Implement uploading data to PaddleCloud

1. Refine data_utils/data.py, reuse process_utterance function.
2. Modified README.
3. Implement uploading data in cloud/upload_data.py
4. Merge branch 'develop' of https://github.com/PaddlePaddle/models into ds2_pcloud

README.md

@@ -2,14 +2,19 @@
 
 ## Installation
 
-Please replace `$PADDLE_INSTALL_DIR` with your own paddle installation directory.
+### Prerequisites
+
+ - **Python = 2.7** only supported;
+ - **cuDNN >= 6.0** is required to utilize NVIDIA GPU platform in the installation of PaddlePaddle, and the **CUDA toolkit** with proper version suitable for cuDNN. The cuDNN library below 6.0 is found to yield a fatal error in batch normalization when handling utterances with long duration in inference.
+
+### Setup
 
 ```
 sh setup.sh
 export LD_LIBRARY_PATH=$PADDLE_INSTALL_DIR/Paddle/third_party/install/warpctc/lib:$LD_LIBRARY_PATH
 ```
 
-For some machines, we also need to install libsndfile1. Details to be added.
+Please replace `$PADDLE_INSTALL_DIR` with your own paddle installation directory.
 
 ## Usage
 
@@ -35,13 +40,13 @@ python datasets/librispeech/librispeech.py --help
 ### Preparing for Training
 
 ```
-python compute_mean_std.py
+python tools/compute_mean_std.py
 ```
 
 It will compute mean and stdandard deviation for audio features, and save them to a file with a default name `./mean_std.npz`. This file will be used in both training and inferencing. The default feature of audio data is power spectrum, and the mfcc feature is also supported. To train and infer based on mfcc feature, please generate this file by
 
 ```
-python compute_mean_std.py --specgram_type mfcc
+python tools/compute_mean_std.py --specgram_type mfcc
 ```
 
 and specify ```--specgram_type mfcc``` when running train.py, infer.py, evaluator.py or tune.py.
@@ -49,7 +54,7 @@ and specify ```--specgram_type mfcc``` when running train.py, infer.py, evaluato
 More help for arguments:
 
 ```
-python compute_mean_std.py --help
+python tools/compute_mean_std.py --help
 ```
 
 ### Training
@@ -138,3 +143,28 @@ python tune.py --help
 ```
 
 Then reset parameters with the tuning result before inference or evaluating.
+
+### Playing with the ASR Demo
+
+A real-time ASR demo is built for users to try out the ASR model with their own voice. Please do the following installation on the machine you'd like to run the demo's client (no need for the machine running the demo's server).
+
+For example, on MAC OS X:
+
+```
+brew install portaudio
+pip install pyaudio
+pip install pynput
+```
+After a model and language model is prepared, we can first start the demo's server:
+
+```
+CUDA_VISIBLE_DEVICES=0 python demo_server.py
+```
+And then in another console, start the demo's client:
+
+```
+python demo_client.py
+```
+On the client console, press and hold the "white-space" key on the keyboard to start talking, until you finish your speech and then release the "white-space" key. The decoding results (infered transcription) will be displayed.
+
+It could be possible to start the server and the client in two seperate machines, e.g. `demo_client.py` is usually started in a machine with a microphone hardware, while `demo_server.py` is usually started in a remote server with powerful GPUs. Please first make sure that these two machines have network access to each other, and then use `--host_ip` and `--host_port` to indicate the server machine's actual IP address (instead of the `localhost` as default) and TCP port, in both `demo_server.py` and `demo_client.py`.

cloud/README.md

-#DeepSpeech2 on paddle cloud
+# Run DS2 on PaddleCloud
 
-## Run DS2 by public data
+>Note: Make sure current directory is `models/deep_speech_2/cloud/`
 
-**Step1: ** Make sure current dir is `models/deep_speech_2/cloud/`
+## Step1  Configure data set
 
-**Step2:**  Submit job by cmd: `sh pcloud_submit.sh`
+You can configure your input data and output path in pcloud_submit.sh:
 
+-  `TRAIN_MANIFEST`： Absolute path of train data manifest file  in local file system.This file has format as bellow:
+
+```
+{"audio_filepath": "/home/disk1/LibriSpeech/dev-clean/1272/128104/1272-128104-0000.flac", "duration": 5.855, "text
+": "mister quilter is the ..."}
+{"audio_filepath": "/home/disk1/LibriSpeech/dev-clean/1272/128104/1272-128104-0001.flac", "duration": 4.815, "text
+": "nor is mister ..."}
+```
+
+- `TEST_MANIFEST`: Absolute path of train data manifest file in local filesystem.This file has format like  TRAIN_MANIFEST.
+
+- `VOCAB_FILE`:  Absolute path of vocabulary file in local filesytem.
+- `MEAN_STD_FILE`: Absolute path of vocabulary file in local filesytem.
+- `CLOUD_DATA_DIR:`  Absolute path in PaddleCloud filesystem. We will upload local train data to this directory.
+- `CLOUD_MODEL_DIR`: Absolute path in PaddleCloud filesystem. PaddleCloud trainer will save model to this directory.
+
+
+>Note: Upload will be skipped if target file has existed in  ${CLOUD_DATA_DIR}.
+
+## Step2  Configure computation resource
+
+You can configure computation resource in pcloud_submit.sh:
+```
+# Configure computation resource and submit job to PaddleCloud
+ paddlecloud submit \
+ -image wanghaoshuang/pcloud_ds2:latest \
+ -jobname ${JOB_NAME} \
+ -cpu 4 \
+ -gpu 4 \
+ -memory 10Gi \
+ -parallelism 1 \
+ -pscpu 1 \
+ -pservers 1 \
+ -psmemory 10Gi \
+ -passes 1 \
+ -entry "sh pcloud_train.sh ${CLOUD_DATA_DIR} ${CLOUD_MODEL_DIR}" \
+ ${DS2_PATH}
+```
+For more information, please refer to[PaddleCloud](https://github.com/PaddlePaddle/cloud/blob/develop/doc/usage_cn.md#提交任务)
+
+## Step3  Configure algorithm options
+You can configure algorithm options in pcloud_train.sh:
+```
+python train.py \
+--use_gpu=1 \
+--trainer_count=4 \
+--batch_size=256 \
+--mean_std_filepath=$MEAN_STD_FILE \
+--train_manifest_path='./local.train.manifest' \
+--dev_manifest_path='./local.test.manifest' \
+--vocab_filepath=$VOCAB_PATH \
+--output_model_dir=${MODEL_PATH}
+```
+You can get more information about algorithm options by follow command:
+```
+cd ..
+python train.py --help
+```
+
+## Step4  Submit job
 ```
 $ sh pcloud_submit.sh
-$ uploading: deepspeech.tar.gz...
-$ uploading: pcloud_prepare_data.py...
-$ uploading: pcloud_split_data.py...
-$ uploading: pcloud_submit.sh...
-$ uploading: pcloud_train.sh...
-$ deepspeech20170727130129 submited.
 ```
-The we can get job name 'deepspeech20170727130129' at last line
 
-**Step3:** Get logs from paddle cloud by cmd: `paddlecloud logs -n 10000 deepspeech20170727130129`.
 
+## Step5 Get logs
 ```
 $ paddlecloud logs -n 10000 deepspeech20170727130129
 ```
-[More  options and cmd about paddle cloud](https://github.com/PaddlePaddle/cloud/blob/develop/doc/usage_cn.md)
-
-## Run DS2 by customize data
-TODO
+For more information, please refer to [PaddleCloud client](https://github.com/PaddlePaddle/cloud/blob/develop/doc/usage_cn.md#下载并配置paddlecloud) or get help by follow command:
+```
+paddlecloud --help
+```

cloud/pcloud_submit.sh

-#
-TRAIN_MANIFEST="/home/work/wanghaoshuang/ds2/pcloud/models/deep_speech_2/datasets/manifest.dev"
-TEST_MANIFEST="/home/work/wanghaoshuang/ds2/pcloud/models/deep_speech_2/datasets/manifest.dev"
-VOCAB_PATH="/home/work/wanghaoshuang/ds2/pcloud/models/deep_speech_2/datasets/vocab/eng_vocab.txt"
-MEAN_STD_PATH="/home/work/wanghaoshuang/ds2/pcloud/models/deep_speech_2/compute_mean_std.py"
-CLOUD_DATA_DIR="/pfs/dlnel/home/wanghaoshuang@baidu.com/deepspeech2/data"
-CLOUD_MODEL_DIR="/pfs/dlnel/home/wanghaoshuang@baidu.com/deepspeech2/model"
+# Configure input data set in local filesystem
+TRAIN_MANIFEST="/home/work/demo/ds2/pcloud/models/deep_speech_2/datasets/manifest.dev"
+TEST_MANIFEST="/home/work/demo/ds2/pcloud/models/deep_speech_2/datasets/manifest.dev"
+VOCAB_FILE="/home/work/demo/ds2/pcloud/models/deep_speech_2/datasets/vocab/eng_vocab.txt"
+MEAN_STD_FILE="/home/work/demo/ds2/pcloud/models/deep_speech_2/mean_std.npz"
+
+# Configure output path in PaddleCloud filesystem
+CLOUD_DATA_DIR="/pfs/dlnel/home/demo/deepspeech2/data"
+CLOUD_MODEL_DIR="/pfs/dlnel/home/demo/deepspeech2/model"
+
+# Pack and upload local data to PaddleCloud filesystem
+python upload_data.py \
+--train_manifest_path=${TRAIN_MANIFEST} \
+--test_manifest_path=${TEST_MANIFEST} \
+--vocab_file=${VOCAB_FILE} \
+--mean_std_file=${MEAN_STD_FILE} \
+--cloud_data_path=${CLOUD_DATA_DIR}
 
+JOB_NAME=deepspeech`date +%Y%m%d%H%M%S`
 DS2_PATH=${PWD%/*}
+cp -f  pcloud_train.sh ${DS2_PATH}
 
-rm -rf ./tmp
-mkdir ./tmp
-
-paddlecloud ls ${CLOUD_DATA_DIR}/mean_std.npz
-if [ $? -ne 0 ];then
-    cp -f  ${MEAN_STD_PATH} ./tmp/mean_std.npz
-    paddlecloud file put ./tmp/mean_std.npz  ${CLOUD_DATA_DIR}/
-fi
-
-paddlecloud ls ${CLOUD_DATA_DIR}/vocab.txt
-if [ $? -ne 0 ];then
-    cp -f  ${VOCAB_PATH} ./tmp/vocab.txt
-    paddlecloud file put ./tmp/vocab.txt  ${CLOUD_DATA_DIR}/
-fi
-
-paddlecloud ls ${CLOUD_DATA_DIR}/cloud.train.manifest
-if [ $? -ne 0 ];then
-python prepare_data.py \
---manifest_path=${TRAIN_MANIFEST} \
---out_tar_path="./tmp/cloud.train.tar" \
---out_manifest_path="tmp/cloud.train.manifest"
-paddlecloud file put ./tmp/cloud.train.tar ${CLOUD_DATA_DIR}/
-paddlecloud file put ./tmp/cloud.train.manifest ${CLOUD_DATA_DIR}/
-fi
-
-paddlecloud ls ${CLOUD_DATA_DIR}/cloud.test.manifest
-if [ $? -ne 0 ];then
-python prepare_data.py \
---manifest_path=${TEST_MANIFEST} \
---out_tar_path="./tmp/cloud.test.tar" \
---out_manifest_path="tmp/cloud.test.manifest"
-paddlecloud file put ./tmp/cloud.test.tar ${CLOUD_DATA_DIR}/
-paddlecloud file put ./tmp/cloud.test.manifest ${CLOUD_DATA_DIR}/
-fi
-
-rm -rf ./tmp
-
-JOB_NAME=deepspeech`date +%Y%m%d%H%M%S`
-cp pcloud_train.sh ${DS2_PATH}
+# Configure computation resource and submit job to PaddleCloud
 paddlecloud submit \
--image bootstrapper:5000/wanghaoshuang/pcloud_ds2:latest-gpu-cudnn \
+-image bootstrapper:5000/wanghaoshuang/pcloud_ds2:latest \
 -jobname ${JOB_NAME} \
 -cpu 4 \
 -gpu 4 \
@@ -58,5 +32,7 @@ paddlecloud submit \
 -pservers 1 \
 -psmemory 10Gi \
 -passes 1 \
--entry "sh pcloud_train.sh ${CLOUD_DATA_DIR} ${CLOUD_MODEl_DIR}" \
+-entry "sh pcloud_train.sh ${CLOUD_DATA_DIR} ${CLOUD_MODEL_DIR}" \
 ${DS2_PATH}
+
+rm ${DS2_PATH}/pcloud_train.sh

cloud/pcloud_train.sh

 DATA_PATH=$1
 MODEL_PATH=$2
-#setted by user
 TRAIN_MANI=${DATA_PATH}/cloud.train.manifest
-#setted by user
 DEV_MANI=${DATA_PATH}/cloud.test.manifest
-#setted by user
 TRAIN_TAR=${DATA_PATH}/cloud.train.tar
-#setted by user
 DEV_TAR=${DATA_PATH}/cloud.test.tar
-#setted by user
-VOCAB_PATH=${DATA_PATH}/eng_vocab.txt
-#setted by user
+VOCAB_PATH=${DATA_PATH}/vocab.txt
 MEAN_STD_FILE=${DATA_PATH}/mean_std.npz
 
 # split train data for each pcloud node
@@ -28,8 +22,10 @@ python ./cloud/split_data.py \
 python train.py \
 --use_gpu=1 \
 --trainer_count=4 \
---batch_size=256 \
+--batch_size=32 \
+--num_threads_data=4 \
 --mean_std_filepath=$MEAN_STD_FILE \
 --train_manifest_path='./local.train.manifest' \
 --dev_manifest_path='./local.test.manifest' \
 --vocab_filepath=$VOCAB_PATH \
+--output_model_dir=${MODEL_PATH}

cloud/prepare_data.py

-"""
-This tool is used for preparing data for DeepSpeech2 trainning on paddle cloud.
-
-Steps:
-1. Read original manifest and get the local path of sound files.
-2. Tar all local sound files into one tar file.
-3. Modify original manifest to remove the local path information.
-
-Finally, we will get a tar file and a manifest with sound file name, duration
-and text.
-"""
-import json
-import os
-import tarfile
-import sys
-import argparse
-sys.path.append('../')
-from data_utils.utils import read_manifest
-
-parser = argparse.ArgumentParser(description=__doc__)
-parser.add_argument(
-    "--manifest_path",
-    default="../datasets/manifest.train",
-    type=str,
-    help="Manifest of target data. (default: %(default)s)")
-parser.add_argument(
-    "--out_tar_path",
-    default="./tmp/cloud.train.tar",
-    type=str,
-    help="Output tar file path. (default: %(default)s)")
-parser.add_argument(
-    "--out_manifest_path",
-    default="./tmp/cloud.train.manifest",
-    type=str,
-    help="Manifest of output data. (default: %(default)s)")
-args = parser.parse_args()
-
-
-def gen_pcloud_data(manifest_path, out_tar_path, out_manifest_path):
-    '''
-    1. According manifest, tar sound files into out_tar_path
-    2. Generate a new manifest for output tar file
-    '''
-    out_tar = tarfile.open(out_tar_path, 'w')
-    manifest = read_manifest(manifest_path)
-    results = []
-    for json_data in manifest:
-        sound_file = json_data['audio_filepath']
-        filename = os.path.basename(sound_file)
-        out_tar.add(sound_file, arcname=filename)
-        json_data['audio_filepath'] = filename
-        results.append("%s\n" % json.dumps(json_data))
-    with open(out_manifest_path, 'w') as out_manifest:
-        out_manifest.writelines(results)
-    out_manifest.close()
-    out_tar.close()
-
-
-if __name__ == '__main__':
-    gen_pcloud_data(args.manifest_path, args.out_tar_path,
-                    args.out_manifest_path)

cloud/upload_data.py

+"""
+This tool is used for preparing data for DeepSpeech2 trainning on paddle cloud.
+
+Steps:
+1. Read original manifest and get the local path of sound files.
+2. Tar all local sound files into one tar file.
+3. Modify original manifest to remove the local path information.
+
+Finally, we will get a tar file and a manifest with sound file name, duration
+and text.
+"""
+import json
+import os
+import tarfile
+import sys
+import argparse
+import shutil
+sys.path.append('../')
+from data_utils.utils import read_manifest
+from subprocess import call
+
+TRAIN_TAR = "cloud.train.tar"
+TRAIN_MANIFEST = "cloud.train.manifest"
+TEST_TAR = "cloud.test.tar"
+TEST_MANIFEST = "cloud.test.manifest"
+VOCAB_FILE = "vocab.txt"
+MEAN_STD_FILE = "mean_std.npz"
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--train_manifest_path",
+    default="../datasets/manifest.train",
+    type=str,
+    help="Manifest file of train data. (default: %(default)s)")
+parser.add_argument(
+    "--test_manifest_path",
+    default="../datasets/manifest.test",
+    type=str,
+    help="Manifest file of test data. (default: %(default)s)")
+parser.add_argument(
+    "--vocab_file",
+    default="../datasets/vocab/eng_vocab.txt",
+    type=str,
+    help="Vocab file to be uploaded to paddlecloud. (default: %(default)s)")
+parser.add_argument(
+    "--mean_std_file",
+    default="../mean_std.npz",
+    type=str,
+    help="mean_std file to be uploaded to paddlecloud. (default: %(default)s)")
+parser.add_argument(
+    "--cloud_data_path",
+    required=True,
+    default="",
+    type=str,
+    help="Destination path on  paddlecloud. (default: %(default)s)")
+args = parser.parse_args()
+
+parser.add_argument(
+    "--local_tmp_path",
+    default="./tmp/",
+    type=str,
+    help="Local directory for storing temporary  data. (default: %(default)s)")
+args = parser.parse_args()
+
+
+def pack_data(manifest_path, out_tar_path, out_manifest_path):
+    '''
+    1. According manifest, tar sound files into out_tar_path
+    2. Generate a new manifest for output tar file
+    '''
+    out_tar = tarfile.open(out_tar_path, 'w')
+    manifest = read_manifest(manifest_path)
+    results = []
+    for json_data in manifest:
+        sound_file = json_data['audio_filepath']
+        filename = os.path.basename(sound_file)
+        out_tar.add(sound_file, arcname=filename)
+        json_data['audio_filepath'] = filename
+        results.append("%s\n" % json.dumps(json_data))
+    with open(out_manifest_path, 'w') as out_manifest:
+        out_manifest.writelines(results)
+    out_manifest.close()
+    out_tar.close()
+
+
+if __name__ == '__main__':
+    cloud_train_manifest = "%s/%s" % (args.cloud_data_path, TRAIN_MANIFEST)
+    cloud_train_tar = "%s/%s" % (args.cloud_data_path, TRAIN_TAR)
+    cloud_test_manifest = "%s/%s" % (args.cloud_data_path, TEST_MANIFEST)
+    cloud_test_tar = "%s/%s" % (args.cloud_data_path, TEST_TAR)
+    cloud_vocab_file = "%s/%s" % (args.cloud_data_path, VOCAB_FILE)
+    cloud_mean_file = "%s/%s" % (args.cloud_data_path, MEAN_STD_FILE)
+
+    local_train_manifest = "%s/%s" % (args.local_tmp_path, TRAIN_MANIFEST)
+    local_train_tar = "%s/%s" % (args.local_tmp_path, TRAIN_TAR)
+    local_test_manifest = "%s/%s" % (args.local_tmp_path, TEST_MANIFEST)
+    local_test_tar = "%s/%s" % (args.local_tmp_path, TEST_TAR)
+
+    if os.path.exists(args.local_tmp_path):
+        shutil.rmtree(args.local_tmp_path)
+    os.makedirs(args.local_tmp_path)
+
+    ret = 1
+    # train data
+    if args.train_manifest_path != "":
+        ret = call(['paddlecloud', 'ls', cloud_train_manifest])
+        if ret != 0:
+            print "%s does't exist" % cloud_train_manifest
+            pack_data(args.train_manifest_path, local_train_tar,
+                      local_train_manifest)
+            call([
+                'paddlecloud', 'cp', local_train_manifest, cloud_train_manifest
+            ])
+            call(['paddlecloud', 'cp', local_train_tar, cloud_train_tar])
+
+    # test data
+    if args.test_manifest_path != "":
+        try:
+            ret = call(['paddlecloud', 'ls', cloud_test_manifest])
+        except Exception:
+            ret = 1
+        if ret != 0:
+            pack_data(args.test_manifest_path, local_test_tar,
+                      local_test_manifest)
+            call(
+                ['paddlecloud', 'cp', local_test_manifest, cloud_test_manifest])
+            call(['paddlecloud', 'cp', local_test_tar, cloud_test_tar])
+
+    # vocab file
+    if args.vocab_file != "":
+        try:
+            ret = call(['paddlecloud', 'ls', cloud_vocab_file])
+        except Exception:
+            ret = 1
+        if ret != 0:
+            call(['paddlecloud', 'cp', args.vocab_file, cloud_vocab_file])
+
+    # mean_std file
+    if args.mean_std_file != "":
+        try:
+            ret = call(['paddlecloud', 'ls', cloud_mean_file])
+        except Exception:
+            ret = 1
+        if ret != 0:
+            call(['paddlecloud', 'cp', args.mean_std_file, cloud_mean_file])
+
+    os.removedirs(args.local_tmp_path)

conf/augmentation.config

+[
+    {
+        "type": "shift",
+        "params": {"min_shift_ms": -5,
+                   "max_shift_ms": 5},
+        "prob": 1.0
+    }
+]

conf/augmentation.config.example

+[
+    {
+        "type": "noise",
+        "params": {"min_snr_dB": 40,
+                   "max_snr_dB": 50,
+                   "noise_manifest_path": "datasets/manifest.noise"},
+        "prob": 0.6
+    },
+    {
+        "type": "impulse",
+        "params": {"impulse_manifest_path": "datasets/manifest.impulse"},
+        "prob": 0.5
+    },
+    {
+        "type": "speed",
+        "params": {"min_speed_rate": 0.95,
+                   "max_speed_rate": 1.05},
+        "prob": 0.5
+    },
+    {
+        "type": "shift",
+        "params": {"min_shift_ms": -5,
+                   "max_shift_ms": 5},
+        "prob": 1.0
+    },
+    {
+        "type": "volume",
+        "params": {"min_gain_dBFS": -10,
+                   "max_gain_dBFS": 10},
+        "prob": 0.0
+    },
+    {
+        "type": "bayesian_normal",
+        "params": {"target_db": -20,
+                   "prior_db": -20,
+                   "prior_samples": 100},
+        "prob": 0.0
+    }
+]

data_utils/audio.py

@@ -204,7 +204,7 @@ class AudioSegment(object):
         :raise ValueError: If the sample rates of the two segments are not
                            equal, or if the lengths of segments don't match.
         """
-        if type(self) != type(other):
+        if isinstance(other, type(self)):
             raise TypeError("Cannot add segments of different types: %s "
                             "and %s." % (type(self), type(other)))
         if self._sample_rate != other._sample_rate:
@@ -231,7 +231,7 @@ class AudioSegment(object):
         Note that this is an in-place transformation.
         
         :param gain: Gain in decibels to apply to samples. 
-        :type gain: float
+        :type gain: float|1darray
         """
         self._samples *= 10.**(gain / 20.)
 
@@ -457,9 +457,9 @@ class AudioSegment(object):
                             audio segments when resample is not allowed.
         """
         if allow_resample and self.sample_rate != impulse_segment.sample_rate:
-            impulse_segment = impulse_segment.resample(self.sample_rate)
+            impulse_segment.resample(self.sample_rate)
         if self.sample_rate != impulse_segment.sample_rate:
-            raise ValueError("Impulse segment's sample rate (%d Hz) is not"
+            raise ValueError("Impulse segment's sample rate (%d Hz) is not "
                              "equal to base signal sample rate (%d Hz)." %
                              (impulse_segment.sample_rate, self.sample_rate))
         samples = signal.fftconvolve(self.samples, impulse_segment.samples,

data_utils/augmentor/augmentation.py

@@ -8,6 +8,8 @@ import random
 from data_utils.augmentor.volume_perturb import VolumePerturbAugmentor
 from data_utils.augmentor.shift_perturb import ShiftPerturbAugmentor
 from data_utils.augmentor.speed_perturb import SpeedPerturbAugmentor
+from data_utils.augmentor.noise_perturb import NoisePerturbAugmentor
+from data_utils.augmentor.impulse_response import ImpulseResponseAugmentor
 from data_utils.augmentor.resample import ResampleAugmentor
 from data_utils.augmentor.online_bayesian_normalization import \
      OnlineBayesianNormalizationAugmentor
@@ -23,21 +25,46 @@ class AugmentationPipeline(object):
     string, e.g.
     
     .. code-block::
-        
-        '[{"type": "volume",
-           "params": {"min_gain_dBFS": -15,
-                      "max_gain_dBFS": 15},
-           "prob": 0.5},
-          {"type": "speed",
-           "params": {"min_speed_rate": 0.8,
-                      "max_speed_rate": 1.2},
-           "prob": 0.5}
-         ]' 
 
+        [ {
+                "type": "noise",
+                "params": {"min_snr_dB": 10,
+                           "max_snr_dB": 20,
+                           "noise_manifest_path": "datasets/manifest.noise"},
+                "prob": 0.0
+            },
+            {
+                "type": "speed",
+                "params": {"min_speed_rate": 0.9,
+                           "max_speed_rate": 1.1},
+                "prob": 1.0
+            },
+            {
+                "type": "shift",
+                "params": {"min_shift_ms": -5,
+                           "max_shift_ms": 5},
+                "prob": 1.0
+            },
+            {
+                "type": "volume",
+                "params": {"min_gain_dBFS": -10,
+                           "max_gain_dBFS": 10},
+                "prob": 0.0
+            },
+            {
+                "type": "bayesian_normal",
+                "params": {"target_db": -20,
+                           "prior_db": -20,
+                           "prior_samples": 100},
+                "prob": 0.0
+            }
+        ]
+        
     This augmentation configuration inserts two augmentation models
     into the pipeline, with one is VolumePerturbAugmentor and the other
     SpeedPerturbAugmentor. "prob" indicates the probability of the current
-    augmentor to take effect.
+    augmentor to take effect. If "prob" is zero, the augmentor does not take
+    effect.
 
     :param augmentation_config: Augmentation configuration in json string.
     :type augmentation_config: str
@@ -60,7 +87,7 @@ class AugmentationPipeline(object):
         :type audio_segment: AudioSegmenet|SpeechSegment
         """
         for augmentor, rate in zip(self._augmentors, self._rates):
-            if self._rng.uniform(0., 1.) <= rate:
+            if self._rng.uniform(0., 1.) < rate:
                 augmentor.transform_audio(audio_segment)
 
     def _parse_pipeline_from(self, config_json):
@@ -89,5 +116,9 @@ class AugmentationPipeline(object):
             return ResampleAugmentor(self._rng, **params)
         elif augmentor_type == "bayesian_normal":
             return OnlineBayesianNormalizationAugmentor(self._rng, **params)
+        elif augmentor_type == "noise":
+            return NoisePerturbAugmentor(self._rng, **params)
+        elif augmentor_type == "impulse":
+            return ImpulseResponseAugmentor(self._rng, **params)
         else:
             raise ValueError("Unknown augmentor type [%s]." % augmentor_type)

data_utils/augmentor/impulse_response.py

+"""Contains the impulse response augmentation model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from data_utils.augmentor.base import AugmentorBase
+from data_utils import utils
+from data_utils.audio import AudioSegment
+
+
+class ImpulseResponseAugmentor(AugmentorBase):
+    """Augmentation model for adding impulse response effect.
+    
+    :param rng: Random generator object.
+    :type rng: random.Random
+    :param impulse_manifest_path: Manifest path for impulse audio data.
+    :type impulse_manifest_path: basestring 
+    """
+
+    def __init__(self, rng, impulse_manifest_path):
+        self._rng = rng
+        self._impulse_manifest = utils.read_manifest(
+            manifest_path=impulse_manifest_path)
+
+    def transform_audio(self, audio_segment):
+        """Add impulse response effect.
+
+        Note that this is an in-place transformation.
+
+        :param audio_segment: Audio segment to add effects to.
+        :type audio_segment: AudioSegmenet|SpeechSegment
+        """
+        impulse_json = self._rng.sample(self._impulse_manifest, 1)[0]
+        impulse_segment = AudioSegment.from_file(impulse_json['audio_filepath'])
+        audio_segment.convolve(impulse_segment, allow_resample=True)

data_utils/augmentor/noise_perturb.py

+"""Contains the noise perturb augmentation model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from data_utils.augmentor.base import AugmentorBase
+from data_utils import utils
+from data_utils.audio import AudioSegment
+
+
+class NoisePerturbAugmentor(AugmentorBase):
+    """Augmentation model for adding background noise.
+    
+    :param rng: Random generator object.
+    :type rng: random.Random
+    :param min_snr_dB: Minimal signal noise ratio, in decibels.
+    :type min_snr_dB: float
+    :param max_snr_dB: Maximal signal noise ratio, in decibels.
+    :type max_snr_dB: float
+    :param noise_manifest_path: Manifest path for noise audio data.
+    :type noise_manifest_path: basestring 
+    """
+
+    def __init__(self, rng, min_snr_dB, max_snr_dB, noise_manifest_path):
+        self._min_snr_dB = min_snr_dB
+        self._max_snr_dB = max_snr_dB
+        self._rng = rng
+        self._noise_manifest = utils.read_manifest(
+            manifest_path=noise_manifest_path)
+
+    def transform_audio(self, audio_segment):
+        """Add background noise audio.
+
+        Note that this is an in-place transformation.
+
+        :param audio_segment: Audio segment to add effects to.
+        :type audio_segment: AudioSegmenet|SpeechSegment
+        """
+        noise_json = self._rng.sample(self._noise_manifest, 1)[0]
+        if noise_json['duration'] < audio_segment.duration:
+            raise RuntimeError("The duration of sampled noise audio is smaller "
+                               "than the audio segment to add effects to.")
+        diff_duration = noise_json['duration'] - audio_segment.duration
+        start = self._rng.uniform(0, diff_duration)
+        end = start + audio_segment.duration
+        noise_segment = AudioSegment.slice_from_file(
+            noise_json['audio_filepath'], start=start, end=end)
+        snr_dB = self._rng.uniform(self._min_snr_dB, self._max_snr_dB)
+        audio_segment.add_noise(
+            noise_segment, snr_dB, allow_downsampling=True, rng=self._rng)

data_utils/data.py

@@ -72,7 +72,7 @@ class DataGenerator(object):
                  max_freq=None,
                  specgram_type='linear',
                  use_dB_normalization=True,
-                 num_threads=multiprocessing.cpu_count(),
+                 num_threads=multiprocessing.cpu_count() // 2,
                  random_seed=0):
         self._max_duration = max_duration
         self._min_duration = min_duration
@@ -94,6 +94,23 @@ class DataGenerator(object):
         self.tar2info = {}
         self.tar2object = {}
 
+    def process_utterance(self, filename, transcript):
+        """Load, augment, featurize and normalize for speech data.
+
+        :param filename: Audio filepath
+        :type filename: basestring | file
+        :param transcript: Transcription text.
+        :type transcript: basestring
+        :return: Tuple of audio feature tensor and list of token ids for
+                 transcription.
+        :rtype: tuple of (2darray, list)
+        """
+        speech_segment = SpeechSegment.from_file(filename, transcript)
+        self._augmentation_pipeline.transform_audio(speech_segment)
+        specgram, text_ids = self._speech_featurizer.featurize(speech_segment)
+        specgram = self._normalizer.apply(specgram)
+        return specgram, text_ids
+
     def batch_reader_creator(self,
                              manifest_path,
                              batch_size,
@@ -163,7 +180,7 @@ class DataGenerator(object):
                         manifest, batch_size, clipped=True)
                 elif shuffle_method == "instance_shuffle":
                     self._rng.shuffle(manifest)
-                elif not shuffle_method:
+                elif shuffle_method == None:
                     pass
                 else:
                     raise ValueError("Unknown shuffle method %s." %
@@ -210,8 +227,8 @@ class DataGenerator(object):
         return self._speech_featurizer.vocab_list
 
     def _parse_tar(self, file):
-        """
-        Parse a tar file to get a tarfile object and a map containing tarinfoes
+        """Parse a tar file to get a tarfile object
+        and a map containing tarinfoes
         """
         result = {}
         f = tarfile.open(file)
@@ -219,14 +236,14 @@ class DataGenerator(object):
             result[tarinfo.name] = tarinfo
         return f, result
 
-    def _read_soundbytes(self, filepath):
-        """
-        Read bytes from file.
-        If filepath startwith tar, we will read bytes from tar file
+    def _get_file_object(self, file):
+        """Get file object by file path.
+        If file startwith tar, it will return a tar file object
         and cached tar file info for next reading request.
+        It will return file directly, if the type of file is not str.
         """
-        if filepath.startswith('tar:'):
-            tarpath, filename = filepath.split(':', 1)[1].split('#', 1)
+        if file.startswith('tar:'):
+            tarpath, filename = file.split(':', 1)[1].split('#', 1)
             if 'tar2info' not in local_data.__dict__:
                 local_data.tar2info = {}
             if 'tar2object' not in local_data.__dict__:
@@ -236,18 +253,9 @@ class DataGenerator(object):
                 local_data.tar2info[tarpath] = infoes
                 local_data.tar2object[tarpath] = object
             return local_data.tar2object[tarpath].extractfile(
-                local_data.tar2info[tarpath][filename]).read()
+                local_data.tar2info[tarpath][filename])
         else:
-            return open(filepath).read()
-
-    def _process_utterance(self, filename, transcript):
-        """Load, augment, featurize and normalize for speech data."""
-        speech_segment = SpeechSegment.from_bytes(
-            self._read_soundbytes(filename), transcript)
-        self._augmentation_pipeline.transform_audio(speech_segment)
-        specgram, text_ids = self._speech_featurizer.featurize(speech_segment)
-        specgram = self._normalizer.apply(specgram)
-        return specgram, text_ids
+            return open(file)
 
     def _instance_reader_creator(self, manifest):
         """
@@ -263,8 +271,9 @@ class DataGenerator(object):
                 yield instance
 
         def mapper(instance):
-            return self._process_utterance(instance["audio_filepath"],
-                                           instance["text"])
+            return self.process_utterance(
+                self._get_file_object(instance["audio_filepath"]),
+                instance["text"])
 
         return paddle.reader.xmap_readers(
             mapper, reader, self._num_threads, 1024, order=True)

data_utils/featurizer/audio_featurizer.py

@@ -166,21 +166,18 @@ class AudioFeaturizer(object):
                              "window size.")
         # compute 13 cepstral coefficients, and the first one is replaced
         # by log(frame energy)
-        mfcc_feat = mfcc(
-            signal=samples,
-            samplerate=sample_rate,
-            winlen=0.001 * window_ms,
-            winstep=0.001 * stride_ms,
-            highfreq=max_freq)
+        mfcc_feat = np.transpose(
+            mfcc(
+                signal=samples,
+                samplerate=sample_rate,
+                winlen=0.001 * window_ms,
+                winstep=0.001 * stride_ms,
+                highfreq=max_freq))
         # Deltas
         d_mfcc_feat = delta(mfcc_feat, 2)
         # Deltas-Deltas
         dd_mfcc_feat = delta(d_mfcc_feat, 2)
         # concat above three features
-        concat_mfcc_feat = [
-            np.concatenate((mfcc_feat[i], d_mfcc_feat[i], dd_mfcc_feat[i]))
-            for i in xrange(len(mfcc_feat))
-        ]
-        # transpose to be consistent with the linear specgram situation
-        concat_mfcc_feat = np.transpose(concat_mfcc_feat)
+        concat_mfcc_feat = np.concatenate(
+            (mfcc_feat, d_mfcc_feat, dd_mfcc_feat))
         return concat_mfcc_feat

data_utils/featurizer/text_featurizer.py

@@ -4,6 +4,7 @@ from __future__ import division
 from __future__ import print_function
 
 import os
+import codecs
 
 
 class TextFeaturizer(object):
@@ -59,7 +60,7 @@ class TextFeaturizer(object):
     def _load_vocabulary_from_file(self, vocab_filepath):
         """Load vocabulary from file."""
         vocab_lines = []
-        with open(vocab_filepath, 'r') as file:
+        with codecs.open(vocab_filepath, 'r', 'utf-8') as file:
             vocab_lines.extend(file.readlines())
         vocab_list = [line[:-1] for line in vocab_lines]
         vocab_dict = dict(

data_utils/speech.py

@@ -115,7 +115,7 @@ class SpeechSegment(AudioSegment):
                  speech file.
         :rtype: SpeechSegment
         """
-        audio = Audiosegment.slice_from_file(filepath, start, end)
+        audio = AudioSegment.slice_from_file(filepath, start, end)
         return cls(audio.samples, audio.sample_rate, transcript)
 
     @classmethod

data_utils/utils.py

@@ -4,15 +4,16 @@ from __future__ import division
 from __future__ import print_function
 
 import json
+import codecs
 
 
 def read_manifest(manifest_path, max_duration=float('inf'), min_duration=0.0):
     """Load and parse manifest file.
-    
+
     Instances with durations outside [min_duration, max_duration] will be
     filtered out.
 
-    :param manifest_path: Manifest file to load and parse. 
+    :param manifest_path: Manifest file to load and parse.
     :type manifest_path: basestring
     :param max_duration: Maximal duration in seconds for instance filter.
     :type max_duration: float
@@ -23,7 +24,7 @@ def read_manifest(manifest_path, max_duration=float('inf'), min_duration=0.0):
     :raises IOError: If failed to parse the manifest.
     """
     manifest = []
-    for json_line in open(manifest_path):
+    for json_line in codecs.open(manifest_path, 'r', 'utf-8'):
         try:
             json_data = json.loads(json_line)
         except Exception as e:

datasets/librispeech/librispeech.py

@@ -11,11 +11,12 @@ from __future__ import print_function
 
 import distutils.util
 import os
-import wget
+import sys
 import tarfile
 import argparse
 import soundfile
 import json
+import codecs
 from paddle.v2.dataset.common import md5file
 
 DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset/speech')
@@ -66,7 +67,7 @@ def download(url, md5sum, target_dir):
     filepath = os.path.join(target_dir, url.split("/")[-1])
     if not (os.path.exists(filepath) and md5file(filepath) == md5sum):
         print("Downloading %s ..." % url)
-        wget.download(url, target_dir)
+        os.system("wget -c " + url + " -P " + target_dir)
         print("\nMD5 Chesksum %s ..." % filepath)
         if not md5file(filepath) == md5sum:
             raise RuntimeError("MD5 checksum failed.")
@@ -112,7 +113,7 @@ def create_manifest(data_dir, manifest_path):
                         'duration': duration,
                         'text': text
                     }))
-    with open(manifest_path, 'w') as out_file:
+    with codecs.open(manifest_path, 'w', 'utf-8') as out_file:
         for line in json_lines:
             out_file.write(line + '\n')
 

datasets/noise/chime3_background.py

+"""Prepare CHiME3 background data.
+
+Download, unpack and create manifest files.
+Manifest file is a json-format file with each line containing the
+meta data (i.e. audio filepath, transcript and audio duration)
+of each audio file in the data set.
+"""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import distutils.util
+import os
+import wget
+import zipfile
+import argparse
+import soundfile
+import json
+from paddle.v2.dataset.common import md5file
+
+DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset/speech')
+
+URL = "https://d4s.myairbridge.com/packagev2/AG0Y3DNBE5IWRRTV/?dlid=W19XG7T0NNHB027139H0EQ"
+MD5 = "c3ff512618d7a67d4f85566ea1bc39ec"
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--target_dir",
+    default=DATA_HOME + "/chime3_background",
+    type=str,
+    help="Directory to save the dataset. (default: %(default)s)")
+parser.add_argument(
+    "--manifest_filepath",
+    default="manifest.chime3.background",
+    type=str,
+    help="Filepath for output manifests. (default: %(default)s)")
+args = parser.parse_args()
+
+
+def download(url, md5sum, target_dir, filename=None):
+    """Download file from url to target_dir, and check md5sum."""
+    if filename == None:
+        filename = url.split("/")[-1]
+    if not os.path.exists(target_dir): os.makedirs(target_dir)
+    filepath = os.path.join(target_dir, filename)
+    if not (os.path.exists(filepath) and md5file(filepath) == md5sum):
+        print("Downloading %s ..." % url)
+        wget.download(url, target_dir)
+        print("\nMD5 Chesksum %s ..." % filepath)
+        if not md5file(filepath) == md5sum:
+            raise RuntimeError("MD5 checksum failed.")
+    else:
+        print("File exists, skip downloading. (%s)" % filepath)
+    return filepath
+
+
+def unpack(filepath, target_dir):
+    """Unpack the file to the target_dir."""
+    print("Unpacking %s ..." % filepath)
+    if filepath.endswith('.zip'):
+        zip = zipfile.ZipFile(filepath, 'r')
+        zip.extractall(target_dir)
+        zip.close()
+    elif filepath.endswith('.tar') or filepath.endswith('.tar.gz'):
+        tar = zipfile.open(filepath)
+        tar.extractall(target_dir)
+        tar.close()
+    else:
+        raise ValueError("File format is not supported for unpacking.")
+
+
+def create_manifest(data_dir, manifest_path):
+    """Create a manifest json file summarizing the data set, with each line
+    containing the meta data (i.e. audio filepath, transcription text, audio
+    duration) of each audio file within the data set.
+    """
+    print("Creating manifest %s ..." % manifest_path)
+    json_lines = []
+    for subfolder, _, filelist in sorted(os.walk(data_dir)):
+        for filename in filelist:
+            if filename.endswith('.wav'):
+                filepath = os.path.join(data_dir, subfolder, filename)
+                audio_data, samplerate = soundfile.read(filepath)
+                duration = float(len(audio_data)) / samplerate
+                json_lines.append(
+                    json.dumps({
+                        'audio_filepath': filepath,
+                        'duration': duration,
+                        'text': ''
+                    }))
+    with open(manifest_path, 'w') as out_file:
+        for line in json_lines:
+            out_file.write(line + '\n')
+
+
+def prepare_chime3(url, md5sum, target_dir, manifest_path):
+    """Download, unpack and create summmary manifest file."""
+    if not os.path.exists(os.path.join(target_dir, "CHiME3")):
+        # download
+        filepath = download(url, md5sum, target_dir,
+                            "myairbridge-AG0Y3DNBE5IWRRTV.zip")
+        # unpack
+        unpack(filepath, target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_bus.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_caf.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_ped.zip'), target_dir)
+        unpack(
+            os.path.join(target_dir, 'CHiME3_background_str.zip'), target_dir)
+    else:
+        print("Skip downloading and unpacking. Data already exists in %s." %
+              target_dir)
+    # create manifest json file
+    create_manifest(target_dir, manifest_path)
+
+
+def main():
+    prepare_chime3(
+        url=URL,
+        md5sum=MD5,
+        target_dir=args.target_dir,
+        manifest_path=args.manifest_filepath)
+
+
+if __name__ == '__main__':
+    main()

datasets/run_noise.sh

+cd noise 
+python chime3_background.py
+if [ $? -ne 0 ]; then
+    echo "Prepare CHiME3 background noise failed. Terminated."
+    exit 1
+fi
+cd -
+
+cat noise/manifest.* > manifest.noise
+echo "All done."

decoder.py

@@ -205,9 +205,9 @@ def ctc_beam_search_decoder_batch(probs_split,
     :type num_processes: int
     :param cutoff_prob: Cutoff probability in pruning,
                         default 1.0, no pruning.
+    :type cutoff_prob: float
     :param num_processes: Number of parallel processes.
     :type num_processes: int
-    :type cutoff_prob: float
     :param ext_scoring_func: External scoring function for
                             partially decoded sentence, e.g. word count
                             or language model.

demo_client.py

+"""Client-end for the ASR demo."""
+from pynput import keyboard
+import struct
+import socket
+import sys
+import argparse
+import pyaudio
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--host_ip",
+    default="localhost",
+    type=str,
+    help="Server IP address. (default: %(default)s)")
+parser.add_argument(
+    "--host_port",
+    default=8086,
+    type=int,
+    help="Server Port. (default: %(default)s)")
+args = parser.parse_args()
+
+is_recording = False
+enable_trigger_record = True
+
+
+def on_press(key):
+    """On-press keyboard callback function."""
+    global is_recording, enable_trigger_record
+    if key == keyboard.Key.space:
+        if (not is_recording) and enable_trigger_record:
+            sys.stdout.write("Start Recording ... ")
+            sys.stdout.flush()
+            is_recording = True
+
+
+def on_release(key):
+    """On-release keyboard callback function."""
+    global is_recording, enable_trigger_record
+    if key == keyboard.Key.esc:
+        return False
+    elif key == keyboard.Key.space:
+        if is_recording == True:
+            is_recording = False
+
+
+data_list = []
+
+
+def callback(in_data, frame_count, time_info, status):
+    """Audio recorder's stream callback function."""
+    global data_list, is_recording, enable_trigger_record
+    if is_recording:
+        data_list.append(in_data)
+        enable_trigger_record = False
+    elif len(data_list) > 0:
+        # Connect to server and send data
+        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+        sock.connect((args.host_ip, args.host_port))
+        sent = ''.join(data_list)
+        sock.sendall(struct.pack('>i', len(sent)) + sent)
+        print('Speech[length=%d] Sent.' % len(sent))
+        # Receive data from the server and shut down
+        received = sock.recv(1024)
+        print "Recognition Results: {}".format(received)
+        sock.close()
+        data_list = []
+    enable_trigger_record = True
+    return (in_data, pyaudio.paContinue)
+
+
+def main():
+    # prepare audio recorder
+    p = pyaudio.PyAudio()
+    stream = p.open(
+        format=pyaudio.paInt32,
+        channels=1,
+        rate=16000,
+        input=True,
+        stream_callback=callback)
+    stream.start_stream()
+
+    # prepare keyboard listener
+    with keyboard.Listener(
+            on_press=on_press, on_release=on_release) as listener:
+        listener.join()
+
+    # close up
+    stream.stop_stream()
+    stream.close()
+    p.terminate()
+
+
+if __name__ == "__main__":
+    main()

demo_server.py

+"""Server-end for the ASR demo."""
+import os
+import time
+import random
+import argparse
+import distutils.util
+from time import gmtime, strftime
+import SocketServer
+import struct
+import wave
+import paddle.v2 as paddle
+from utils import print_arguments
+from data_utils.data import DataGenerator
+from model import DeepSpeech2Model
+from data_utils.utils import read_manifest
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--host_ip",
+    default="localhost",
+    type=str,
+    help="Server IP address. (default: %(default)s)")
+parser.add_argument(
+    "--host_port",
+    default=8086,
+    type=int,
+    help="Server Port. (default: %(default)s)")
+parser.add_argument(
+    "--speech_save_dir",
+    default="demo_cache",
+    type=str,
+    help="Directory for saving demo speech. (default: %(default)s)")
+parser.add_argument(
+    "--vocab_filepath",
+    default='datasets/vocab/eng_vocab.txt',
+    type=str,
+    help="Vocabulary filepath. (default: %(default)s)")
+parser.add_argument(
+    "--mean_std_filepath",
+    default='mean_std.npz',
+    type=str,
+    help="Manifest path for normalizer. (default: %(default)s)")
+parser.add_argument(
+    "--warmup_manifest_path",
+    default='datasets/manifest.test',
+    type=str,
+    help="Manifest path for warmup test. (default: %(default)s)")
+parser.add_argument(
+    "--specgram_type",
+    default='linear',
+    type=str,
+    help="Feature type of audio data: 'linear' (power spectrum)"
+    " or 'mfcc'. (default: %(default)s)")
+parser.add_argument(
+    "--num_conv_layers",
+    default=2,
+    type=int,
+    help="Convolution layer number. (default: %(default)s)")
+parser.add_argument(
+    "--num_rnn_layers",
+    default=3,
+    type=int,
+    help="RNN layer number. (default: %(default)s)")
+parser.add_argument(
+    "--rnn_layer_size",
+    default=512,
+    type=int,
+    help="RNN layer cell number. (default: %(default)s)")
+parser.add_argument(
+    "--use_gpu",
+    default=True,
+    type=distutils.util.strtobool,
+    help="Use gpu or not. (default: %(default)s)")
+parser.add_argument(
+    "--model_filepath",
+    default='checkpoints/params.latest.tar.gz',
+    type=str,
+    help="Model filepath. (default: %(default)s)")
+parser.add_argument(
+    "--decode_method",
+    default='beam_search',
+    type=str,
+    help="Method for ctc decoding: best_path or beam_search. "
+    "(default: %(default)s)")
+parser.add_argument(
+    "--beam_size",
+    default=100,
+    type=int,
+    help="Width for beam search decoding. (default: %(default)d)")
+parser.add_argument(
+    "--language_model_path",
+    default="lm/data/common_crawl_00.prune01111.trie.klm",
+    type=str,
+    help="Path for language model. (default: %(default)s)")
+parser.add_argument(
+    "--alpha",
+    default=0.36,
+    type=float,
+    help="Parameter associated with language model. (default: %(default)f)")
+parser.add_argument(
+    "--beta",
+    default=0.25,
+    type=float,
+    help="Parameter associated with word count. (default: %(default)f)")
+parser.add_argument(
+    "--cutoff_prob",
+    default=0.99,
+    type=float,
+    help="The cutoff probability of pruning"
+    "in beam search. (default: %(default)f)")
+args = parser.parse_args()
+
+
+class AsrTCPServer(SocketServer.TCPServer):
+    """The ASR TCP Server."""
+
+    def __init__(self,
+                 server_address,
+                 RequestHandlerClass,
+                 speech_save_dir,
+                 audio_process_handler,
+                 bind_and_activate=True):
+        self.speech_save_dir = speech_save_dir
+        self.audio_process_handler = audio_process_handler
+        SocketServer.TCPServer.__init__(
+            self, server_address, RequestHandlerClass, bind_and_activate=True)
+
+
+class AsrRequestHandler(SocketServer.BaseRequestHandler):
+    """The ASR request handler."""
+
+    def handle(self):
+        # receive data through TCP socket
+        chunk = self.request.recv(1024)
+        target_len = struct.unpack('>i', chunk[:4])[0]
+        data = chunk[4:]
+        while len(data) < target_len:
+            chunk = self.request.recv(1024)
+            data += chunk
+        # write to file
+        filename = self._write_to_file(data)
+
+        print("Received utterance[length=%d] from %s, saved to %s." %
+              (len(data), self.client_address[0], filename))
+        start_time = time.time()
+        transcript = self.server.audio_process_handler(filename)
+        finish_time = time.time()
+        print("Response Time: %f, Transcript: %s" %
+              (finish_time - start_time, transcript))
+        self.request.sendall(transcript)
+
+    def _write_to_file(self, data):
+        # prepare save dir and filename
+        if not os.path.exists(self.server.speech_save_dir):
+            os.mkdir(self.server.speech_save_dir)
+        timestamp = strftime("%Y%m%d%H%M%S", gmtime())
+        out_filename = os.path.join(
+            self.server.speech_save_dir,
+            timestamp + "_" + self.client_address[0] + ".wav")
+        # write to wav file
+        file = wave.open(out_filename, 'wb')
+        file.setnchannels(1)
+        file.setsampwidth(4)
+        file.setframerate(16000)
+        file.writeframes(data)
+        file.close()
+        return out_filename
+
+
+def warm_up_test(audio_process_handler,
+                 manifest_path,
+                 num_test_cases,
+                 random_seed=0):
+    """Warming-up test."""
+    manifest = read_manifest(manifest_path)
+    rng = random.Random(random_seed)
+    samples = rng.sample(manifest, num_test_cases)
+    for idx, sample in enumerate(samples):
+        print("Warm-up Test Case %d: %s", idx, sample['audio_filepath'])
+        start_time = time.time()
+        transcript = audio_process_handler(sample['audio_filepath'])
+        finish_time = time.time()
+        print("Response Time: %f, Transcript: %s" %
+              (finish_time - start_time, transcript))
+
+
+def start_server():
+    """Start the ASR server"""
+    # prepare data generator
+    data_generator = DataGenerator(
+        vocab_filepath=args.vocab_filepath,
+        mean_std_filepath=args.mean_std_filepath,
+        augmentation_config='{}',
+        specgram_type=args.specgram_type,
+        num_threads=1)
+    # prepare ASR model
+    ds2_model = DeepSpeech2Model(
+        vocab_size=data_generator.vocab_size,
+        num_conv_layers=args.num_conv_layers,
+        num_rnn_layers=args.num_rnn_layers,
+        rnn_layer_size=args.rnn_layer_size,
+        pretrained_model_path=args.model_filepath)
+
+    # prepare ASR inference handler
+    def file_to_transcript(filename):
+        feature = data_generator.process_utterance(filename, "")
+        result_transcript = ds2_model.infer_batch(
+            infer_data=[feature],
+            decode_method=args.decode_method,
+            beam_alpha=args.alpha,
+            beam_beta=args.beta,
+            beam_size=args.beam_size,
+            cutoff_prob=args.cutoff_prob,
+            vocab_list=data_generator.vocab_list,
+            language_model_path=args.language_model_path,
+            num_processes=1)
+        return result_transcript[0]
+
+    # warming up with utterrances sampled from Librispeech
+    print('-----------------------------------------------------------')
+    print('Warming up ...')
+    warm_up_test(
+        audio_process_handler=file_to_transcript,
+        manifest_path=args.warmup_manifest_path,
+        num_test_cases=3)
+    print('-----------------------------------------------------------')
+
+    # start the server
+    server = AsrTCPServer(
+        server_address=(args.host_ip, args.host_port),
+        RequestHandlerClass=AsrRequestHandler,
+        speech_save_dir=args.speech_save_dir,
+        audio_process_handler=file_to_transcript)
+    print("ASR Server Started.")
+    server.serve_forever()
+
+
+def main():
+    print_arguments(args)
+    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    start_server()
+
+
+if __name__ == "__main__":
+    main()

error_rate.py

@@ -10,47 +10,54 @@ import numpy as np
 
 
 def _levenshtein_distance(ref, hyp):
-    """Levenshtein distance is a string metric for measuring the difference between
-    two sequences. Informally, the levenshtein disctance is defined as the minimum
-    number of single-character edits (substitutions, insertions or deletions) 
-    required to change one word into the other. We can naturally extend the edits to 
-    word level when calculate levenshtein disctance for two sentences.
+    """Levenshtein distance is a string metric for measuring the difference
+    between two sequences. Informally, the levenshtein disctance is defined as
+    the minimum number of single-character edits (substitutions, insertions or
+    deletions) required to change one word into the other. We can naturally
+    extend the edits to word level when calculate levenshtein disctance for
+    two sentences.
     """
-    ref_len = len(ref)
-    hyp_len = len(hyp)
+    m = len(ref)
+    n = len(hyp)
 
     # special case
     if ref == hyp:
         return 0
-    if ref_len == 0:
-        return hyp_len
-    if hyp_len == 0:
-        return ref_len
+    if m == 0:
+        return n
+    if n == 0:
+        return m
 
-    distance = np.zeros((ref_len + 1, hyp_len + 1), dtype=np.int32)
+    if m < n:
+        ref, hyp = hyp, ref
+        m, n = n, m
+
+    # use O(min(m, n)) space
+    distance = np.zeros((2, n + 1), dtype=np.int32)
 
     # initialize distance matrix
-    for j in xrange(hyp_len + 1):
+    for j in xrange(n + 1):
         distance[0][j] = j
-    for i in xrange(ref_len + 1):
-        distance[i][0] = i
 
     # calculate levenshtein distance
-    for i in xrange(1, ref_len + 1):
-        for j in xrange(1, hyp_len + 1):
+    for i in xrange(1, m + 1):
+        prev_row_idx = (i - 1) % 2
+        cur_row_idx = i % 2
+        distance[cur_row_idx][0] = i
+        for j in xrange(1, n + 1):
             if ref[i - 1] == hyp[j - 1]:
-                distance[i][j] = distance[i - 1][j - 1]
+                distance[cur_row_idx][j] = distance[prev_row_idx][j - 1]
             else:
-                s_num = distance[i - 1][j - 1] + 1
-                i_num = distance[i][j - 1] + 1
-                d_num = distance[i - 1][j] + 1
-                distance[i][j] = min(s_num, i_num, d_num)
+                s_num = distance[prev_row_idx][j - 1] + 1
+                i_num = distance[cur_row_idx][j - 1] + 1
+                d_num = distance[prev_row_idx][j] + 1
+                distance[cur_row_idx][j] = min(s_num, i_num, d_num)
 
-    return distance[ref_len][hyp_len]
+    return distance[m % 2][n]
 
 
 def wer(reference, hypothesis, ignore_case=False, delimiter=' '):
-    """Calculate word error rate (WER). WER compares reference text and 
+    """Calculate word error rate (WER). WER compares reference text and
     hypothesis text in word-level. WER is defined as:
 
     .. math::
@@ -65,8 +72,8 @@ def wer(reference, hypothesis, ignore_case=False, delimiter=' '):
         Iw is the number of words inserted,
         Nw is the number of words in the reference
 
-    We can use levenshtein distance to calculate WER. Please draw an attention that 
-    empty items will be removed when splitting sentences by delimiter.
+    We can use levenshtein distance to calculate WER. Please draw an attention
+    that empty items will be removed when splitting sentences by delimiter.
 
     :param reference: The reference sentence.
     :type reference: basestring
@@ -95,7 +102,7 @@ def wer(reference, hypothesis, ignore_case=False, delimiter=' '):
     return wer
 
 
-def cer(reference, hypothesis, ignore_case=False):
+def cer(reference, hypothesis, ignore_case=False, remove_space=False):
     """Calculate charactor error rate (CER). CER compares reference text and
     hypothesis text in char-level. CER is defined as:
 
@@ -111,10 +118,10 @@ def cer(reference, hypothesis, ignore_case=False):
         Ic is the number of characters inserted
         Nc is the number of characters in the reference
 
-    We can use levenshtein distance to calculate CER. Chinese input should be 
-    encoded to unicode. Please draw an attention that the leading and tailing 
-    white space characters will be truncated and multiple consecutive white 
-    space characters in a sentence will be replaced by one white space character.
+    We can use levenshtein distance to calculate CER. Chinese input should be
+    encoded to unicode. Please draw an attention that the leading and tailing
+    space characters will be truncated and multiple consecutive space
+    characters in a sentence will be replaced by one space character.
 
     :param reference: The reference sentence.
     :type reference: basestring
@@ -122,6 +129,8 @@ def cer(reference, hypothesis, ignore_case=False):
     :type hypothesis: basestring
     :param ignore_case: Whether case-sensitive or not.
     :type ignore_case: bool
+    :param remove_space: Whether remove internal space characters
+    :type remove_space: bool
     :return: Character error rate.
     :rtype: float
     :raises ValueError: If the reference length is zero.
@@ -130,8 +139,12 @@ def cer(reference, hypothesis, ignore_case=False):
         reference = reference.lower()
         hypothesis = hypothesis.lower()
 
-    reference = ' '.join(filter(None, reference.split(' ')))
-    hypothesis = ' '.join(filter(None, hypothesis.split(' ')))
+    join_char = ' '
+    if remove_space == True:
+        join_char = ''
+
+    reference = join_char.join(filter(None, reference.split(' ')))
+    hypothesis = join_char.join(filter(None, hypothesis.split(' ')))
 
     if len(reference) == 0:
         raise ValueError("Length of reference should be greater than 0.")

evaluate.py

@@ -5,20 +5,24 @@ from __future__ import print_function
 
 import distutils.util
 import argparse
-import gzip
+import multiprocessing
 import paddle.v2 as paddle
 from data_utils.data import DataGenerator
-from model import deep_speech2
-from decoder import *
-from lm.lm_scorer import LmScorer
-from error_rate import wer
+from model import DeepSpeech2Model
+from error_rate import wer, cer
+import utils
 
 parser = argparse.ArgumentParser(description=__doc__)
 parser.add_argument(
     "--batch_size",
-    default=100,
+    default=128,
     type=int,
     help="Minibatch size for evaluation. (default: %(default)s)")
+parser.add_argument(
+    "--trainer_count",
+    default=8,
+    type=int,
+    help="Trainer number. (default: %(default)s)")
 parser.add_argument(
     "--num_conv_layers",
     default=2,
@@ -41,12 +45,12 @@ parser.add_argument(
     help="Use gpu or not. (default: %(default)s)")
 parser.add_argument(
     "--num_threads_data",
-    default=multiprocessing.cpu_count(),
+    default=multiprocessing.cpu_count() // 2,
     type=int,
     help="Number of cpu threads for preprocessing data. (default: %(default)s)")
 parser.add_argument(
     "--num_processes_beam_search",
-    default=multiprocessing.cpu_count(),
+    default=multiprocessing.cpu_count() // 2,
     type=int,
     help="Number of cpu processes for beam search. (default: %(default)s)")
 parser.add_argument(
@@ -58,8 +62,8 @@ parser.add_argument(
     "--decode_method",
     default='beam_search',
     type=str,
-    help="Method for ctc decoding, best_path or beam_search. (default: %(default)s)"
-)
+    help="Method for ctc decoding, best_path or beam_search. "
+    "(default: %(default)s)")
 parser.add_argument(
     "--language_model_path",
     default="lm/data/common_crawl_00.prune01111.trie.klm",
@@ -67,12 +71,12 @@ parser.add_argument(
     help="Path for language model. (default: %(default)s)")
 parser.add_argument(
     "--alpha",
-    default=0.26,
+    default=0.36,
     type=float,
     help="Parameter associated with language model. (default: %(default)f)")
 parser.add_argument(
     "--beta",
-    default=0.1,
+    default=0.25,
     type=float,
     help="Parameter associated with word count. (default: %(default)f)")
 parser.add_argument(
@@ -107,42 +111,25 @@ parser.add_argument(
     default='datasets/vocab/eng_vocab.txt',
     type=str,
     help="Vocabulary filepath. (default: %(default)s)")
+parser.add_argument(
+    "--error_rate_type",
+    default='wer',
+    choices=['wer', 'cer'],
+    type=str,
+    help="Error rate type for evaluation. 'wer' for word error rate and 'cer' "
+    "for character error rate. "
+    "(default: %(default)s)")
 args = parser.parse_args()
 
 
 def evaluate():
     """Evaluate on whole test data for DeepSpeech2."""
-    # initialize data generator
     data_generator = DataGenerator(
         vocab_filepath=args.vocab_filepath,
         mean_std_filepath=args.mean_std_filepath,
         augmentation_config='{}',
         specgram_type=args.specgram_type,
         num_threads=args.num_threads_data)
-
-    # create network config
-    # paddle.data_type.dense_array is used for variable batch input.
-    # The size 161 * 161 is only an placeholder value and the real shape
-    # of input batch data will be induced during training.
-    audio_data = paddle.layer.data(
-        name="audio_spectrogram", type=paddle.data_type.dense_array(161 * 161))
-    text_data = paddle.layer.data(
-        name="transcript_text",
-        type=paddle.data_type.integer_value_sequence(data_generator.vocab_size))
-    output_probs = deep_speech2(
-        audio_data=audio_data,
-        text_data=text_data,
-        dict_size=data_generator.vocab_size,
-        num_conv_layers=args.num_conv_layers,
-        num_rnn_layers=args.num_rnn_layers,
-        rnn_size=args.rnn_layer_size,
-        is_inference=True)
-
-    # load parameters
-    parameters = paddle.parameters.Parameters.from_tar(
-        gzip.open(args.model_filepath))
-
-    # prepare infer data
     batch_reader = data_generator.batch_reader_creator(
         manifest_path=args.decode_manifest_path,
         batch_size=args.batch_size,
@@ -150,61 +137,42 @@ def evaluate():
         sortagrad=False,
         shuffle_method=None)
 
-    # define inferer
-    inferer = paddle.inference.Inference(
-        output_layer=output_probs, parameters=parameters)
-
-    # initialize external scorer for beam search decoding
-    if args.decode_method == 'beam_search':
-        ext_scorer = LmScorer(args.alpha, args.beta, args.language_model_path)
+    ds2_model = DeepSpeech2Model(
+        vocab_size=data_generator.vocab_size,
+        num_conv_layers=args.num_conv_layers,
+        num_rnn_layers=args.num_rnn_layers,
+        rnn_layer_size=args.rnn_layer_size,
+        pretrained_model_path=args.model_filepath)
 
-    wer_counter, wer_sum = 0, 0.0
+    error_rate_func = cer if args.error_rate_type == 'cer' else wer
+    error_sum, num_ins = 0.0, 0
     for infer_data in batch_reader():
-        # run inference
-        infer_results = inferer.infer(input=infer_data)
-        num_steps = len(infer_results) // len(infer_data)
-        probs_split = [
-            infer_results[i * num_steps:(i + 1) * num_steps]
-            for i in xrange(0, len(infer_data))
-        ]
-        # target transcription
-        target_transcription = [
-            ''.join([
-                data_generator.vocab_list[index] for index in infer_data[i][1]
-            ]) for i, probs in enumerate(probs_split)
+        result_transcripts = ds2_model.infer_batch(
+            infer_data=infer_data,
+            decode_method=args.decode_method,
+            beam_alpha=args.alpha,
+            beam_beta=args.beta,
+            beam_size=args.beam_size,
+            cutoff_prob=args.cutoff_prob,
+            vocab_list=data_generator.vocab_list,
+            language_model_path=args.language_model_path,
+            num_processes=args.num_processes_beam_search)
+        target_transcripts = [
+            ''.join([data_generator.vocab_list[token] for token in transcript])
+            for _, transcript in infer_data
         ]
-        # decode and print
-        # best path decode
-        if args.decode_method == "best_path":
-            for i, probs in enumerate(probs_split):
-                output_transcription = ctc_best_path_decoder(
-                    probs_seq=probs, vocabulary=data_generator.vocab_list)
-                wer_sum += wer(target_transcription[i], output_transcription)
-                wer_counter += 1
-        # beam search decode
-        elif args.decode_method == "beam_search":
-            # beam search using multiple processes
-            beam_search_results = ctc_beam_search_decoder_batch(
-                probs_split=probs_split,
-                vocabulary=data_generator.vocab_list,
-                beam_size=args.beam_size,
-                blank_id=len(data_generator.vocab_list),
-                num_processes=args.num_processes_beam_search,
-                ext_scoring_func=ext_scorer,
-                cutoff_prob=args.cutoff_prob, )
-            for i, beam_search_result in enumerate(beam_search_results):
-                wer_sum += wer(target_transcription[i],
-                               beam_search_result[0][1])
-                wer_counter += 1
-        else:
-            raise ValueError("Decoding method [%s] is not supported." %
-                             decode_method)
-
-    print("Final WER = %f" % (wer_sum / wer_counter))
+        for target, result in zip(target_transcripts, result_transcripts):
+            error_sum += error_rate_func(target, result)
+            num_ins += 1
+        print("Error rate [%s] (%d/?) = %f" %
+              (args.error_rate_type, num_ins, error_sum / num_ins))
+    print("Final error rate [%s] (%d/%d) = %f" %
+          (args.error_rate_type, num_ins, num_ins, error_sum / num_ins))
 
 
 def main():
-    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    utils.print_arguments(args)
+    paddle.init(use_gpu=args.use_gpu, trainer_count=args.trainer_count)
     evaluate()
 
 

infer.py

@@ -4,15 +4,12 @@ from __future__ import division
 from __future__ import print_function
 
 import argparse
-import gzip
 import distutils.util
 import multiprocessing
 import paddle.v2 as paddle
 from data_utils.data import DataGenerator
-from model import deep_speech2
-from decoder import *
-from lm.lm_scorer import LmScorer
-from error_rate import wer
+from model import DeepSpeech2Model
+from error_rate import wer, cer
 import utils
 
 parser = argparse.ArgumentParser(description=__doc__)
@@ -43,12 +40,12 @@ parser.add_argument(
     help="Use gpu or not. (default: %(default)s)")
 parser.add_argument(
     "--num_threads_data",
-    default=multiprocessing.cpu_count(),
+    default=1,
     type=int,
     help="Number of cpu threads for preprocessing data. (default: %(default)s)")
 parser.add_argument(
     "--num_processes_beam_search",
-    default=multiprocessing.cpu_count(),
+    default=multiprocessing.cpu_count() // 2,
     type=int,
     help="Number of cpu processes for beam search. (default: %(default)s)")
 parser.add_argument(
@@ -57,6 +54,11 @@ parser.add_argument(
     type=str,
     help="Feature type of audio data: 'linear' (power spectrum)"
     " or 'mfcc'. (default: %(default)s)")
+parser.add_argument(
+    "--trainer_count",
+    default=8,
+    type=int,
+    help="Trainer number. (default: %(default)s)")
 parser.add_argument(
     "--mean_std_filepath",
     default='mean_std.npz',
@@ -81,18 +83,13 @@ parser.add_argument(
     "--decode_method",
     default='beam_search',
     type=str,
-    help="Method for ctc decoding: best_path or beam_search. (default: %(default)s)"
-)
+    help="Method for ctc decoding: best_path or beam_search. "
+    "(default: %(default)s)")
 parser.add_argument(
     "--beam_size",
     default=500,
     type=int,
     help="Width for beam search decoding. (default: %(default)d)")
-parser.add_argument(
-    "--num_results_per_sample",
-    default=1,
-    type=int,
-    help="Number of output per sample in beam search. (default: %(default)d)")
 parser.add_argument(
     "--language_model_path",
     default="lm/data/common_crawl_00.prune01111.trie.klm",
@@ -100,12 +97,12 @@ parser.add_argument(
     help="Path for language model. (default: %(default)s)")
 parser.add_argument(
     "--alpha",
-    default=0.26,
+    default=0.36,
     type=float,
     help="Parameter associated with language model. (default: %(default)f)")
 parser.add_argument(
     "--beta",
-    default=0.1,
+    default=0.25,
     type=float,
     help="Parameter associated with word count. (default: %(default)f)")
 parser.add_argument(
@@ -114,42 +111,25 @@ parser.add_argument(
     type=float,
     help="The cutoff probability of pruning"
     "in beam search. (default: %(default)f)")
+parser.add_argument(
+    "--error_rate_type",
+    default='wer',
+    choices=['wer', 'cer'],
+    type=str,
+    help="Error rate type for evaluation. 'wer' for word error rate and 'cer' "
+    "for character error rate. "
+    "(default: %(default)s)")
 args = parser.parse_args()
 
 
 def infer():
     """Inference for DeepSpeech2."""
-    # initialize data generator
     data_generator = DataGenerator(
         vocab_filepath=args.vocab_filepath,
         mean_std_filepath=args.mean_std_filepath,
         augmentation_config='{}',
         specgram_type=args.specgram_type,
         num_threads=args.num_threads_data)
-
-    # create network config
-    # paddle.data_type.dense_array is used for variable batch input.
-    # The size 161 * 161 is only an placeholder value and the real shape
-    # of input batch data will be induced during training.
-    audio_data = paddle.layer.data(
-        name="audio_spectrogram", type=paddle.data_type.dense_array(161 * 161))
-    text_data = paddle.layer.data(
-        name="transcript_text",
-        type=paddle.data_type.integer_value_sequence(data_generator.vocab_size))
-    output_probs = deep_speech2(
-        audio_data=audio_data,
-        text_data=text_data,
-        dict_size=data_generator.vocab_size,
-        num_conv_layers=args.num_conv_layers,
-        num_rnn_layers=args.num_rnn_layers,
-        rnn_size=args.rnn_layer_size,
-        is_inference=True)
-
-    # load parameters
-    parameters = paddle.parameters.Parameters.from_tar(
-        gzip.open(args.model_filepath))
-
-    # prepare infer data
     batch_reader = data_generator.batch_reader_creator(
         manifest_path=args.decode_manifest_path,
         batch_size=args.num_samples,
@@ -158,66 +138,38 @@ def infer():
         shuffle_method=None)
     infer_data = batch_reader().next()
 
-    # run inference
-    infer_results = paddle.infer(
-        output_layer=output_probs, parameters=parameters, input=infer_data)
-    num_steps = len(infer_results) // len(infer_data)
-    probs_split = [
-        infer_results[i * num_steps:(i + 1) * num_steps]
-        for i in xrange(len(infer_data))
-    ]
+    ds2_model = DeepSpeech2Model(
+        vocab_size=data_generator.vocab_size,
+        num_conv_layers=args.num_conv_layers,
+        num_rnn_layers=args.num_rnn_layers,
+        rnn_layer_size=args.rnn_layer_size,
+        pretrained_model_path=args.model_filepath)
+    result_transcripts = ds2_model.infer_batch(
+        infer_data=infer_data,
+        decode_method=args.decode_method,
+        beam_alpha=args.alpha,
+        beam_beta=args.beta,
+        beam_size=args.beam_size,
+        cutoff_prob=args.cutoff_prob,
+        vocab_list=data_generator.vocab_list,
+        language_model_path=args.language_model_path,
+        num_processes=args.num_processes_beam_search)
 
-    # targe transcription
-    target_transcription = [
-        ''.join(
-            [data_generator.vocab_list[index] for index in infer_data[i][1]])
-        for i, probs in enumerate(probs_split)
+    error_rate_func = cer if args.error_rate_type == 'cer' else wer
+    target_transcripts = [
+        ''.join([data_generator.vocab_list[token] for token in transcript])
+        for _, transcript in infer_data
     ]
-
-    ## decode and print
-    # best path decode
-    wer_sum, wer_counter = 0, 0
-    if args.decode_method == "best_path":
-        for i, probs in enumerate(probs_split):
-            best_path_transcription = ctc_best_path_decoder(
-                probs_seq=probs, vocabulary=data_generator.vocab_list)
-            print("\nTarget Transcription: %s\nOutput Transcription: %s" %
-                  (target_transcription[i], best_path_transcription))
-            wer_cur = wer(target_transcription[i], best_path_transcription)
-            wer_sum += wer_cur
-            wer_counter += 1
-            print("cur wer = %f, average wer = %f" %
-                  (wer_cur, wer_sum / wer_counter))
-    # beam search decode
-    elif args.decode_method == "beam_search":
-        ext_scorer = LmScorer(args.alpha, args.beta, args.language_model_path)
-        beam_search_batch_results = ctc_beam_search_decoder_batch(
-            probs_split=probs_split,
-            vocabulary=data_generator.vocab_list,
-            beam_size=args.beam_size,
-            blank_id=len(data_generator.vocab_list),
-            num_processes=args.num_processes_beam_search,
-            cutoff_prob=args.cutoff_prob,
-            ext_scoring_func=ext_scorer, )
-        for i, beam_search_result in enumerate(beam_search_batch_results):
-            print("\nTarget Transcription:\t%s" % target_transcription[i])
-            for index in xrange(args.num_results_per_sample):
-                result = beam_search_result[index]
-                #output: index, log prob, beam result
-                print("Beam %d: %f \t%s" % (index, result[0], result[1]))
-            wer_cur = wer(target_transcription[i], beam_search_result[0][1])
-            wer_sum += wer_cur
-            wer_counter += 1
-            print("cur wer = %f , average wer = %f" %
-                  (wer_cur, wer_sum / wer_counter))
-    else:
-        raise ValueError("Decoding method [%s] is not supported." %
-                         decode_method)
+    for target, result in zip(target_transcripts, result_transcripts):
+        print("\nTarget Transcription: %s\nOutput Transcription: %s" %
+              (target, result))
+        print("Current error rate [%s] = %f" %
+              (args.error_rate_type, error_rate_func(target, result)))
 
 
 def main():
     utils.print_arguments(args)
-    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    paddle.init(use_gpu=args.use_gpu, trainer_count=args.trainer_count)
     infer()
 
 

layer.py

+"""Contains DeepSpeech2 layers."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import paddle.v2 as paddle
+
+
+def conv_bn_layer(input, filter_size, num_channels_in, num_channels_out, stride,
+                  padding, act):
+    """Convolution layer with batch normalization.
+
+    :param input: Input layer.
+    :type input: LayerOutput
+    :param filter_size: The x dimension of a filter kernel. Or input a tuple for
+                        two image dimension.
+    :type filter_size: int|tuple|list
+    :param num_channels_in: Number of input channels.
+    :type num_channels_in: int
+    :type num_channels_out: Number of output channels.
+    :type num_channels_in: out
+    :param padding: The x dimension of the padding. Or input a tuple for two
+                    image dimension.
+    :type padding: int|tuple|list
+    :param act: Activation type.
+    :type act: BaseActivation
+    :return: Batch norm layer after convolution layer.
+    :rtype: LayerOutput
+    """
+    conv_layer = paddle.layer.img_conv(
+        input=input,
+        filter_size=filter_size,
+        num_channels=num_channels_in,
+        num_filters=num_channels_out,
+        stride=stride,
+        padding=padding,
+        act=paddle.activation.Linear(),
+        bias_attr=False)
+    return paddle.layer.batch_norm(input=conv_layer, act=act)
+
+
+def bidirectional_simple_rnn_bn_layer(name, input, size, act):
+    """Bidirectonal simple rnn layer with sequence-wise batch normalization.
+    The batch normalization is only performed on input-state weights.
+
+    :param name: Name of the layer.
+    :type name: string
+    :param input: Input layer.
+    :type input: LayerOutput
+    :param size: Number of RNN cells.
+    :type size: int
+    :param act: Activation type.
+    :type act: BaseActivation
+    :return: Bidirectional simple rnn layer.
+    :rtype: LayerOutput
+    """
+    # input-hidden weights shared across bi-direcitonal rnn.
+    input_proj = paddle.layer.fc(
+        input=input, size=size, act=paddle.activation.Linear(), bias_attr=False)
+    # batch norm is only performed on input-state projection 
+    input_proj_bn = paddle.layer.batch_norm(
+        input=input_proj, act=paddle.activation.Linear())
+    # forward and backward in time
+    forward_simple_rnn = paddle.layer.recurrent(
+        input=input_proj_bn, act=act, reverse=False)
+    backward_simple_rnn = paddle.layer.recurrent(
+        input=input_proj_bn, act=act, reverse=True)
+    return paddle.layer.concat(input=[forward_simple_rnn, backward_simple_rnn])
+
+
+def conv_group(input, num_stacks):
+    """Convolution group with stacked convolution layers.
+
+    :param input: Input layer.
+    :type input: LayerOutput
+    :param num_stacks: Number of stacked convolution layers.
+    :type num_stacks: int
+    :return: Output layer of the convolution group.
+    :rtype: LayerOutput
+    """
+    conv = conv_bn_layer(
+        input=input,
+        filter_size=(11, 41),
+        num_channels_in=1,
+        num_channels_out=32,
+        stride=(3, 2),
+        padding=(5, 20),
+        act=paddle.activation.BRelu())
+    for i in xrange(num_stacks - 1):
+        conv = conv_bn_layer(
+            input=conv,
+            filter_size=(11, 21),
+            num_channels_in=32,
+            num_channels_out=32,
+            stride=(1, 2),
+            padding=(5, 10),
+            act=paddle.activation.BRelu())
+    output_num_channels = 32
+    output_height = 160 // pow(2, num_stacks) + 1
+    return conv, output_num_channels, output_height
+
+
+def rnn_group(input, size, num_stacks):
+    """RNN group with stacked bidirectional simple RNN layers.
+
+    :param input: Input layer.
+    :type input: LayerOutput
+    :param size: Number of RNN cells in each layer.
+    :type size: int
+    :param num_stacks: Number of stacked rnn layers.
+    :type num_stacks: int
+    :return: Output layer of the RNN group.
+    :rtype: LayerOutput
+    """
+    output = input
+    for i in xrange(num_stacks):
+        output = bidirectional_simple_rnn_bn_layer(
+            name=str(i), input=output, size=size, act=paddle.activation.BRelu())
+    return output
+
+
+def deep_speech2(audio_data,
+                 text_data,
+                 dict_size,
+                 num_conv_layers=2,
+                 num_rnn_layers=3,
+                 rnn_size=256):
+    """
+    The whole DeepSpeech2 model structure (a simplified version).
+
+    :param audio_data: Audio spectrogram data layer.
+    :type audio_data: LayerOutput
+    :param text_data: Transcription text data layer.
+    :type text_data: LayerOutput
+    :param dict_size: Dictionary size for tokenized transcription.
+    :type dict_size: int
+    :param num_conv_layers: Number of stacking convolution layers.
+    :type num_conv_layers: int
+    :param num_rnn_layers: Number of stacking RNN layers.
+    :type num_rnn_layers: int
+    :param rnn_size: RNN layer size (number of RNN cells).
+    :type rnn_size: int
+    :return: A tuple of an output unnormalized log probability layer (
+             before softmax) and a ctc cost layer.
+    :rtype: tuple of LayerOutput
+    """
+    # convolution group
+    conv_group_output, conv_group_num_channels, conv_group_height = conv_group(
+        input=audio_data, num_stacks=num_conv_layers)
+    # convert data form convolution feature map to sequence of vectors
+    conv2seq = paddle.layer.block_expand(
+        input=conv_group_output,
+        num_channels=conv_group_num_channels,
+        stride_x=1,
+        stride_y=1,
+        block_x=1,
+        block_y=conv_group_height)
+    # rnn group
+    rnn_group_output = rnn_group(
+        input=conv2seq, size=rnn_size, num_stacks=num_rnn_layers)
+    fc = paddle.layer.fc(
+        input=rnn_group_output,
+        size=dict_size + 1,
+        act=paddle.activation.Linear(),
+        bias_attr=True)
+    # probability distribution with softmax
+    log_probs = paddle.layer.mixed(
+        input=paddle.layer.identity_projection(input=fc),
+        act=paddle.activation.Softmax())
+    # ctc cost
+    ctc_loss = paddle.layer.warp_ctc(
+        input=fc,
+        label=text_data,
+        size=dict_size + 1,
+        blank=dict_size,
+        norm_by_times=True)
+    return log_probs, ctc_loss

model.py

@@ -3,141 +3,240 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import sys
+import os
+import time
+import gzip
+from decoder import *
+from lm.lm_scorer import LmScorer
 import paddle.v2 as paddle
+from layer import *
 
 
-def conv_bn_layer(input, filter_size, num_channels_in, num_channels_out, stride,
-                  padding, act):
-    """
-    Convolution layer with batch normalization.
-    """
-    conv_layer = paddle.layer.img_conv(
-        input=input,
-        filter_size=filter_size,
-        num_channels=num_channels_in,
-        num_filters=num_channels_out,
-        stride=stride,
-        padding=padding,
-        act=paddle.activation.Linear(),
-        bias_attr=False)
-    return paddle.layer.batch_norm(input=conv_layer, act=act)
-
-
-def bidirectional_simple_rnn_bn_layer(name, input, size, act):
-    """
-    Bidirectonal simple rnn layer with sequence-wise batch normalization.
-    The batch normalization is only performed on input-state weights.
-    """
-    # input-hidden weights shared across bi-direcitonal rnn.
-    input_proj = paddle.layer.fc(
-        input=input, size=size, act=paddle.activation.Linear(), bias_attr=False)
-    # batch norm is only performed on input-state projection 
-    input_proj_bn = paddle.layer.batch_norm(
-        input=input_proj, act=paddle.activation.Linear())
-    # forward and backward in time
-    forward_simple_rnn = paddle.layer.recurrent(
-        input=input_proj_bn, act=act, reverse=False)
-    backward_simple_rnn = paddle.layer.recurrent(
-        input=input_proj_bn, act=act, reverse=True)
-    return paddle.layer.concat(input=[forward_simple_rnn, backward_simple_rnn])
-
-
-def conv_group(input, num_stacks):
-    """
-    Convolution group with several stacking convolution layers.
-    """
-    conv = conv_bn_layer(
-        input=input,
-        filter_size=(11, 41),
-        num_channels_in=1,
-        num_channels_out=32,
-        stride=(3, 2),
-        padding=(5, 20),
-        act=paddle.activation.BRelu())
-    for i in xrange(num_stacks - 1):
-        conv = conv_bn_layer(
-            input=conv,
-            filter_size=(11, 21),
-            num_channels_in=32,
-            num_channels_out=32,
-            stride=(1, 2),
-            padding=(5, 10),
-            act=paddle.activation.BRelu())
-    output_num_channels = 32
-    output_height = 160 // pow(2, num_stacks) + 1
-    return conv, output_num_channels, output_height
-
-
-def rnn_group(input, size, num_stacks):
-    """
-    RNN group with several stacking RNN layers.
-    """
-    output = input
-    for i in xrange(num_stacks):
-        output = bidirectional_simple_rnn_bn_layer(
-            name=str(i), input=output, size=size, act=paddle.activation.BRelu())
-    return output
-
-
-def deep_speech2(audio_data,
-                 text_data,
-                 dict_size,
-                 num_conv_layers=2,
-                 num_rnn_layers=3,
-                 rnn_size=256,
-                 is_inference=False):
-    """
-    The whole DeepSpeech2 model structure (a simplified version).
-
-    :param audio_data: Audio spectrogram data layer.
-    :type audio_data: LayerOutput
-    :param text_data: Transcription text data layer.
-    :type text_data: LayerOutput
-    :param dict_size: Dictionary size for tokenized transcription.
-    :type dict_size: int
+class DeepSpeech2Model(object):
+    """DeepSpeech2Model class.
+
+    :param vocab_size: Decoding vocabulary size.
+    :type vocab_size: int
     :param num_conv_layers: Number of stacking convolution layers.
     :type num_conv_layers: int
     :param num_rnn_layers: Number of stacking RNN layers.
     :type num_rnn_layers: int
-    :param rnn_size: RNN layer size (number of RNN cells).
-    :type rnn_size: int
-    :param is_inference: False in the training mode, and True in the
-                         inferene mode.
-    :type is_inference: bool
-    :return: If is_inference set False, return a ctc cost layer;
-             if is_inference set True, return a sequence layer of output
-             probability distribution.
-    :rtype: tuple of LayerOutput
+    :param rnn_layer_size: RNN layer size (number of RNN cells).
+    :type rnn_layer_size: int
+    :param pretrained_model_path: Pretrained model path. If None, will train
+                                  from stratch.
+    :type pretrained_model_path: basestring|None
     """
-    # convolution group
-    conv_group_output, conv_group_num_channels, conv_group_height = conv_group(
-        input=audio_data, num_stacks=num_conv_layers)
-    # convert data form convolution feature map to sequence of vectors
-    conv2seq = paddle.layer.block_expand(
-        input=conv_group_output,
-        num_channels=conv_group_num_channels,
-        stride_x=1,
-        stride_y=1,
-        block_x=1,
-        block_y=conv_group_height)
-    # rnn group
-    rnn_group_output = rnn_group(
-        input=conv2seq, size=rnn_size, num_stacks=num_rnn_layers)
-    fc = paddle.layer.fc(
-        input=rnn_group_output,
-        size=dict_size + 1,
-        act=paddle.activation.Linear(),
-        bias_attr=True)
-    if is_inference:
-        # probability distribution with softmax
-        return paddle.layer.mixed(
-            input=paddle.layer.identity_projection(input=fc),
-            act=paddle.activation.Softmax())
-    else:
-        # ctc cost
-        return paddle.layer.warp_ctc(
-            input=fc,
-            label=text_data,
-            size=dict_size + 1,
-            blank=dict_size,
-            norm_by_times=True)
+
+    def __init__(self, vocab_size, num_conv_layers, num_rnn_layers,
+                 rnn_layer_size, pretrained_model_path):
+        self._create_network(vocab_size, num_conv_layers, num_rnn_layers,
+                             rnn_layer_size)
+        self._create_parameters(pretrained_model_path)
+        self._inferer = None
+        self._loss_inferer = None
+        self._ext_scorer = None
+
+    def train(self,
+              train_batch_reader,
+              dev_batch_reader,
+              feeding_dict,
+              learning_rate,
+              gradient_clipping,
+              num_passes,
+              output_model_dir,
+              num_iterations_print=100):
+        """Train the model.
+
+        :param train_batch_reader: Train data reader.
+        :type train_batch_reader: callable
+        :param dev_batch_reader: Validation data reader.
+        :type dev_batch_reader: callable
+        :param feeding_dict: Feeding is a map of field name and tuple index
+                             of the data that reader returns.
+        :type feeding_dict: dict|list
+        :param learning_rate: Learning rate for ADAM optimizer.
+        :type learning_rate: float
+        :param gradient_clipping: Gradient clipping threshold.
+        :type gradient_clipping: float
+        :param num_passes: Number of training epochs.
+        :type num_passes: int
+        :param num_iterations_print: Number of training iterations for printing
+                                     a training loss.
+        :type rnn_iteratons_print: int
+        :param output_model_dir: Directory for saving the model (every pass).
+        :type output_model_dir: basestring
+        """
+        # prepare model output directory
+        if not os.path.exists(output_model_dir):
+            os.mkdir(output_model_dir)
+
+        # prepare optimizer and trainer
+        optimizer = paddle.optimizer.Adam(
+            learning_rate=learning_rate,
+            gradient_clipping_threshold=gradient_clipping)
+        trainer = paddle.trainer.SGD(
+            cost=self._loss,
+            parameters=self._parameters,
+            update_equation=optimizer)
+
+        # create event handler
+        def event_handler(event):
+            global start_time, cost_sum, cost_counter
+            if isinstance(event, paddle.event.EndIteration):
+                cost_sum += event.cost
+                cost_counter += 1
+                if (event.batch_id + 1) % num_iterations_print == 0:
+                    output_model_path = os.path.join(output_model_dir,
+                                                     "params.latest.tar.gz")
+                    with gzip.open(output_model_path, 'w') as f:
+                        self._parameters.to_tar(f)
+                    print("\nPass: %d, Batch: %d, TrainCost: %f" %
+                          (event.pass_id, event.batch_id + 1,
+                           cost_sum / cost_counter))
+                    cost_sum, cost_counter = 0.0, 0
+                else:
+                    sys.stdout.write('.')
+                    sys.stdout.flush()
+            if isinstance(event, paddle.event.BeginPass):
+                start_time = time.time()
+                cost_sum, cost_counter = 0.0, 0
+            if isinstance(event, paddle.event.EndPass):
+                result = trainer.test(
+                    reader=dev_batch_reader, feeding=feeding_dict)
+                output_model_path = os.path.join(
+                    output_model_dir, "params.pass-%d.tar.gz" % event.pass_id)
+                with gzip.open(output_model_path, 'w') as f:
+                    self._parameters.to_tar(f)
+                print("\n------- Time: %d sec,  Pass: %d, ValidationCost: %s" %
+                      (time.time() - start_time, event.pass_id, result.cost))
+
+        # run train
+        trainer.train(
+            reader=train_batch_reader,
+            event_handler=event_handler,
+            num_passes=num_passes,
+            feeding=feeding_dict)
+
+    def infer_loss_batch(self, infer_data):
+        """Model inference. Infer the ctc loss for a batch of speech
+        utterances.
+
+        :param infer_data: List of utterances to infer, with each utterance a
+                           tuple of audio features and transcription text (empty
+                           string).
+        :type infer_data: list
+        :return: List of ctc loss.
+        :rtype: List of float
+        """
+        # define inferer
+        if self._loss_inferer == None:
+            self._loss_inferer = paddle.inference.Inference(
+                output_layer=self._loss, parameters=self._parameters)
+        # run inference
+        return self._loss_inferer.infer(input=infer_data)
+
+    def infer_batch(self, infer_data, decode_method, beam_alpha, beam_beta,
+                    beam_size, cutoff_prob, vocab_list, language_model_path,
+                    num_processes):
+        """Model inference. Infer the transcription for a batch of speech
+        utterances.
+
+        :param infer_data: List of utterances to infer, with each utterance
+                           consisting of a tuple of audio features and
+                           transcription text (empty string).
+        :type infer_data: list
+        :param decode_method: Decoding method name, 'best_path' or
+                              'beam search'.
+        :param decode_method: string
+        :param beam_alpha: Parameter associated with language model.
+        :type beam_alpha: float
+        :param beam_beta: Parameter associated with word count.
+        :type beam_beta: float
+        :param beam_size: Width for Beam search.
+        :type beam_size: int
+        :param cutoff_prob: Cutoff probability in pruning,
+                            default 1.0, no pruning.
+        :type cutoff_prob: float
+        :param vocab_list: List of tokens in the vocabulary, for decoding.
+        :type vocab_list: list
+        :param language_model_path: Filepath for language model.
+        :type language_model_path: basestring|None
+        :param num_processes: Number of processes (CPU) for decoder.
+        :type num_processes: int
+        :return: List of transcription texts.
+        :rtype: List of basestring
+        """
+        # define inferer
+        if self._inferer == None:
+            self._inferer = paddle.inference.Inference(
+                output_layer=self._log_probs, parameters=self._parameters)
+        # run inference
+        infer_results = self._inferer.infer(input=infer_data)
+        num_steps = len(infer_results) // len(infer_data)
+        probs_split = [
+            infer_results[i * num_steps:(i + 1) * num_steps]
+            for i in xrange(0, len(infer_data))
+        ]
+        # run decoder
+        results = []
+        if decode_method == "best_path":
+            # best path decode
+            for i, probs in enumerate(probs_split):
+                output_transcription = ctc_best_path_decoder(
+                    probs_seq=probs, vocabulary=vocab_list)
+                results.append(output_transcription)
+        elif decode_method == "beam_search":
+            # initialize external scorer
+            if self._ext_scorer == None:
+                self._ext_scorer = LmScorer(beam_alpha, beam_beta,
+                                            language_model_path)
+                self._loaded_lm_path = language_model_path
+            else:
+                self._ext_scorer.reset_params(beam_alpha, beam_beta)
+                assert self._loaded_lm_path == language_model_path
+
+            # beam search decode
+            beam_search_results = ctc_beam_search_decoder_batch(
+                probs_split=probs_split,
+                vocabulary=vocab_list,
+                beam_size=beam_size,
+                blank_id=len(vocab_list),
+                num_processes=num_processes,
+                ext_scoring_func=self._ext_scorer,
+                cutoff_prob=cutoff_prob)
+
+            results = [result[0][1] for result in beam_search_results]
+        else:
+            raise ValueError("Decoding method [%s] is not supported." %
+                             decode_method)
+        return results
+
+    def _create_parameters(self, model_path=None):
+        """Load or create model parameters."""
+        if model_path is None:
+            self._parameters = paddle.parameters.create(self._loss)
+        else:
+            self._parameters = paddle.parameters.Parameters.from_tar(
+                gzip.open(model_path))
+
+    def _create_network(self, vocab_size, num_conv_layers, num_rnn_layers,
+                        rnn_layer_size):
+        """Create data layers and model network."""
+        # paddle.data_type.dense_array is used for variable batch input.
+        # The size 161 * 161 is only an placeholder value and the real shape
+        # of input batch data will be induced during training.
+        audio_data = paddle.layer.data(
+            name="audio_spectrogram",
+            type=paddle.data_type.dense_array(161 * 161))
+        text_data = paddle.layer.data(
+            name="transcript_text",
+            type=paddle.data_type.integer_value_sequence(vocab_size))
+        self._log_probs, self._loss = deep_speech2(
+            audio_data=audio_data,
+            text_data=text_data,
+            dict_size=vocab_size,
+            num_conv_layers=num_conv_layers,
+            num_rnn_layers=num_rnn_layers,
+            rnn_size=rnn_layer_size)

pcloud_train.sh

-DATA_PATH=$1
-MODEL_PATH=$2
-#setted by user
-TRAIN_MANI=${DATA_PATH}/cloud.train.manifest
-#setted by user
-DEV_MANI=${DATA_PATH}/cloud.test.manifest
-#setted by user
-TRAIN_TAR=${DATA_PATH}/cloud.train.tar
-#setted by user
-DEV_TAR=${DATA_PATH}/cloud.test.tar
-#setted by user
-VOCAB_PATH=${DATA_PATH}/eng_vocab.txt
-#setted by user
-MEAN_STD_FILE=${DATA_PATH}/mean_std.npz
-
-# split train data for each pcloud node
-python ./cloud/split_data.py \
---in_manifest_path=$TRAIN_MANI \
---data_tar_path=$TRAIN_TAR \
---out_manifest_path='./local.train.manifest'
-
-# split dev data for each pcloud node
-python ./cloud/split_data.py \
---in_manifest_path=$DEV_MANI \
---data_tar_path=$DEV_TAR \
---out_manifest_path='./local.test.manifest'
-
-python train.py \
---use_gpu=1 \
---trainer_count=4 \
---batch_size=256 \
---mean_std_filepath=$MEAN_STD_FILE \
---train_manifest_path='./local.train.manifest' \
---dev_manifest_path='./local.test.manifest' \
---vocab_filepath=$VOCAB_PATH \

requirements.txt

-wget==3.2
 scipy==0.13.1
 resampy==0.1.5
-https://github.com/kpu/kenlm/archive/master.zip
+SoundFile==0.9.0.post1
 python_speech_features
+https://github.com/luotao1/kenlm/archive/master.zip

setup.sh

@@ -9,25 +9,21 @@ if [ $? != 0 ]; then
     exit 1
 fi
 
-# install package Soundfile
-curl -O "http://www.mega-nerd.com/libsndfile/files/libsndfile-1.0.28.tar.gz"
+# install package libsndfile
+python -c "import soundfile"
 if [ $? != 0 ]; then
-    echo "Download libsndfile-1.0.28.tar.gz failed !!!"
-    exit 1
+    echo "Install package libsndfile into default system path."
+    curl -O "http://www.mega-nerd.com/libsndfile/files/libsndfile-1.0.28.tar.gz"
+    if [ $? != 0 ]; then
+        echo "Download libsndfile-1.0.28.tar.gz failed !!!"
+        exit 1
+    fi
+    tar -zxvf libsndfile-1.0.28.tar.gz
+    cd libsndfile-1.0.28
+    ./configure && make && make install
+    cd ..
+    rm -rf libsndfile-1.0.28
+    rm libsndfile-1.0.28.tar.gz
 fi
-tar -zxvf libsndfile-1.0.28.tar.gz
-cd libsndfile-1.0.28
-./configure && make && make install
-cd -
-rm -rf libsndfile-1.0.28
-rm libsndfile-1.0.28.tar.gz
-pip install SoundFile==0.9.0.post1
-if [ $? != 0 ]; then
-    echo "Install SoundFile failed !!!"
-    exit 1
-fi
-
-# prepare ./checkpoints
-mkdir checkpoints
 
 echo "Install all dependencies successfully."

tests/test_error_rate.py

@@ -11,16 +11,54 @@ import error_rate
 class TestParse(unittest.TestCase):
     def test_wer_1(self):
         ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night'
-        hyp = 'i GOT IT TO the FULLEST i LOVE TO portable FROM OF STORES last night'
+        hyp = 'i GOT IT TO the FULLEST i LOVE TO portable FROM OF STORES last '\
+                'night'
         word_error_rate = error_rate.wer(ref, hyp)
         self.assertTrue(abs(word_error_rate - 0.769230769231) < 1e-6)
 
     def test_wer_2(self):
+        ref = 'as any in england i would say said gamewell proudly that is '\
+                'in his day'
+        hyp = 'as any in england i would say said came well proudly that is '\
+                'in his day'
+        word_error_rate = error_rate.wer(ref, hyp)
+        self.assertTrue(abs(word_error_rate - 0.1333333) < 1e-6)
+
+    def test_wer_3(self):
+        ref = 'the lieutenant governor lilburn w boggs afterward governor '\
+                'was a pronounced mormon hater and throughout the period of '\
+                'the troubles he manifested sympathy with the persecutors'
+        hyp = 'the lieutenant governor little bit how bags afterward '\
+                'governor was a pronounced warman hater and throughout the '\
+                'period of th troubles he manifests sympathy with the '\
+                'persecutors'
+        word_error_rate = error_rate.wer(ref, hyp)
+        self.assertTrue(abs(word_error_rate - 0.2692307692) < 1e-6)
+
+    def test_wer_4(self):
+        ref = 'the wood flamed up splendidly under the large brewing copper '\
+                'and it sighed so deeply'
+        hyp = 'the wood flame do splendidly under the large brewing copper '\
+                'and its side so deeply'
+        word_error_rate = error_rate.wer(ref, hyp)
+        self.assertTrue(abs(word_error_rate - 0.2666666667) < 1e-6)
+
+    def test_wer_5(self):
+        ref = 'all the morning they trudged up the mountain path and at noon '\
+                'unc and ojo sat on a fallen tree trunk and ate the last of '\
+                'the bread which the old munchkin had placed in his pocket'
+        hyp = 'all the morning they trudged up the mountain path and at noon '\
+                'unc in ojo sat on a fallen tree trunk and ate the last of '\
+                'the bread which the old munchkin had placed in his pocket'
+        word_error_rate = error_rate.wer(ref, hyp)
+        self.assertTrue(abs(word_error_rate - 0.027027027) < 1e-6)
+
+    def test_wer_6(self):
         ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night'
         word_error_rate = error_rate.wer(ref, ref)
         self.assertEqual(word_error_rate, 0.0)
 
-    def test_wer_3(self):
+    def test_wer_7(self):
         ref = ' '
         hyp = 'Hypothesis sentence'
         with self.assertRaises(ValueError):
@@ -33,22 +71,40 @@ class TestParse(unittest.TestCase):
         self.assertTrue(abs(char_error_rate - 0.25) < 1e-6)
 
     def test_cer_2(self):
+        ref = 'werewolf'
+        hyp = 'weae  wolf'
+        char_error_rate = error_rate.cer(ref, hyp, remove_space=True)
+        self.assertTrue(abs(char_error_rate - 0.125) < 1e-6)
+
+    def test_cer_3(self):
+        ref = 'were wolf'
+        hyp = 'were  wolf'
+        char_error_rate = error_rate.cer(ref, hyp)
+        self.assertTrue(abs(char_error_rate - 0.0) < 1e-6)
+
+    def test_cer_4(self):
         ref = 'werewolf'
         char_error_rate = error_rate.cer(ref, ref)
         self.assertEqual(char_error_rate, 0.0)
 
-    def test_cer_3(self):
+    def test_cer_5(self):
         ref = u'我是中国人'
         hyp = u'我是 美洲人'
         char_error_rate = error_rate.cer(ref, hyp)
         self.assertTrue(abs(char_error_rate - 0.6) < 1e-6)
 
-    def test_cer_4(self):
+    def test_cer_6(self):
+        ref = u'我 是 中 国 人'
+        hyp = u'我 是 美 洲 人'
+        char_error_rate = error_rate.cer(ref, hyp, remove_space=True)
+        self.assertTrue(abs(char_error_rate - 0.4) < 1e-6)
+
+    def test_cer_7(self):
         ref = u'我是中国人'
         char_error_rate = error_rate.cer(ref, ref)
         self.assertFalse(char_error_rate, 0.0)
 
-    def test_cer_5(self):
+    def test_cer_8(self):
         ref = ''
         hyp = 'Hypothesis'
         with self.assertRaises(ValueError):

tests/test_setup.py

+"""Test Setup."""
+import unittest
+import numpy as np
+import os
+
+
+class TestSetup(unittest.TestCase):
+    def test_soundfile(self):
+        import soundfile as sf
+        # floating point data is typically limited to the interval [-1.0, 1.0],
+        # but smaller/larger values are supported as well
+        data = np.array([[1.75, -1.75], [1.0, -1.0], [0.5, -0.5],
+                         [0.25, -0.25]])
+        file = 'test.wav'
+        sf.write(file, data, 44100, format='WAV', subtype='FLOAT')
+        read, fs = sf.read(file)
+        self.assertTrue(np.all(read == data))
+        self.assertEqual(fs, 44100)
+        os.remove(file)
+
+
+if __name__ == '__main__':
+    unittest.main()

tools/_init_paths.py

+"""Set up paths for DS2"""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os.path
+import sys
+
+
+def add_path(path):
+    if path not in sys.path:
+        sys.path.insert(0, path)
+
+
+this_dir = os.path.dirname(__file__)
+
+# Add project path to PYTHONPATH
+proj_path = os.path.join(this_dir, '..')
+add_path(proj_path)

tools/build_vocab.py

+"""Build vocabulary from manifest files.
+
+Each item in vocabulary file is a character.
+"""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import argparse
+import codecs
+import json
+from collections import Counter
+import os.path
+import _init_paths
+from data_utils import utils
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--manifest_paths",
+    type=str,
+    help="Manifest paths for building vocabulary."
+    "You can provide multiple manifest files.",
+    nargs='+',
+    required=True)
+parser.add_argument(
+    "--count_threshold",
+    default=0,
+    type=int,
+    help="Characters whose counts are below the threshold will be truncated. "
+    "(default: %(default)i)")
+parser.add_argument(
+    "--vocab_path",
+    default='datasets/vocab/zh_vocab.txt',
+    type=str,
+    help="File path to write the vocabulary. (default: %(default)s)")
+args = parser.parse_args()
+
+
+def count_manifest(counter, manifest_path):
+    manifest_jsons = utils.read_manifest(manifest_path)
+    for line_json in manifest_jsons:
+        for char in line_json['text']:
+            counter.update(char)
+
+
+def main():
+    counter = Counter()
+    for manifest_path in args.manifest_paths:
+        count_manifest(counter, manifest_path)
+
+    count_sorted = sorted(counter.items(), key=lambda x: x[1], reverse=True)
+    with codecs.open(args.vocab_path, 'w', 'utf-8') as fout:
+        for char, count in count_sorted:
+            if count < args.count_threshold: break
+            fout.write(char + '\n')
+
+
+if __name__ == '__main__':
+    main()

compute_mean_std.py → tools/compute_mean_std.py

@@ -4,6 +4,7 @@ from __future__ import division
 from __future__ import print_function
 
 import argparse
+import _init_paths
 from data_utils.normalizer import FeatureNormalizer
 from data_utils.augmentor.augmentation import AugmentationPipeline
 from data_utils.featurizer.audio_featurizer import AudioFeaturizer

train.py

@@ -3,15 +3,11 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
-import sys
-import os
 import argparse
-import gzip
-import time
 import distutils.util
 import multiprocessing
 import paddle.v2 as paddle
-from model import deep_speech2
+from model import DeepSpeech2Model
 from data_utils.data import DataGenerator
 import utils
 
@@ -23,6 +19,12 @@ parser.add_argument(
     default=200,
     type=int,
     help="Training pass number. (default: %(default)s)")
+parser.add_argument(
+    "--num_iterations_print",
+    default=100,
+    type=int,
+    help="Number of iterations for every train cost printing. "
+    "(default: %(default)s)")
 parser.add_argument(
     "--num_conv_layers",
     default=2,
@@ -84,7 +86,7 @@ parser.add_argument(
     help="Trainer number. (default: %(default)s)")
 parser.add_argument(
     "--num_threads_data",
-    default=multiprocessing.cpu_count(),
+    default=multiprocessing.cpu_count() // 2,
     type=int,
     help="Number of cpu threads for preprocessing data. (default: %(default)s)")
 parser.add_argument(
@@ -114,11 +116,14 @@ parser.add_argument(
     help="If set None, the training will start from scratch. "
     "Otherwise, the training will resume from "
     "the existing model of this path. (default: %(default)s)")
+parser.add_argument(
+    "--output_model_dir",
+    default="./checkpoints",
+    type=str,
+    help="Directory for saving models. (default: %(default)s)")
 parser.add_argument(
     "--augmentation_config",
-    default='[{"type": "shift", '
-    '"params": {"min_shift_ms": -5, "max_shift_ms": 5},'
-    '"prob": 1.0}]',
+    default=open('conf/augmentation.config', 'r').read(),
     type=str,
     help="Augmentation configuration in json-format. "
     "(default: %(default)s)")
@@ -127,100 +132,48 @@ args = parser.parse_args()
 
 def train():
     """DeepSpeech2 training."""
-
-    # initialize data generator
-    def data_generator():
-        return DataGenerator(
-            vocab_filepath=args.vocab_filepath,
-            mean_std_filepath=args.mean_std_filepath,
-            augmentation_config=args.augmentation_config,
-            max_duration=args.max_duration,
-            min_duration=args.min_duration,
-            specgram_type=args.specgram_type,
-            num_threads=args.num_threads_data)
-
-    train_generator = data_generator()
-    test_generator = data_generator()
-
-    # create network config
-    # paddle.data_type.dense_array is used for variable batch input.
-    # The size 161 * 161 is only an placeholder value and the real shape
-    # of input batch data will be induced during training.
-    audio_data = paddle.layer.data(
-        name="audio_spectrogram", type=paddle.data_type.dense_array(161 * 161))
-    text_data = paddle.layer.data(
-        name="transcript_text",
-        type=paddle.data_type.integer_value_sequence(
-            train_generator.vocab_size))
-    cost = deep_speech2(
-        audio_data=audio_data,
-        text_data=text_data,
-        dict_size=train_generator.vocab_size,
-        num_conv_layers=args.num_conv_layers,
-        num_rnn_layers=args.num_rnn_layers,
-        rnn_size=args.rnn_layer_size,
-        is_inference=False)
-
-    # create/load parameters and optimizer
-    if args.init_model_path is None:
-        parameters = paddle.parameters.create(cost)
-    else:
-        if not os.path.isfile(args.init_model_path):
-            raise IOError("Invalid model!")
-        parameters = paddle.parameters.Parameters.from_tar(
-            gzip.open(args.init_model_path))
-    optimizer = paddle.optimizer.Adam(
-        learning_rate=args.adam_learning_rate, gradient_clipping_threshold=400)
-    trainer = paddle.trainer.SGD(
-        cost=cost, parameters=parameters, update_equation=optimizer)
-
-    # prepare data reader
+    train_generator = DataGenerator(
+        vocab_filepath=args.vocab_filepath,
+        mean_std_filepath=args.mean_std_filepath,
+        augmentation_config=args.augmentation_config,
+        max_duration=args.max_duration,
+        min_duration=args.min_duration,
+        specgram_type=args.specgram_type,
+        num_threads=args.num_threads_data)
+    dev_generator = DataGenerator(
+        vocab_filepath=args.vocab_filepath,
+        mean_std_filepath=args.mean_std_filepath,
+        augmentation_config="{}",
+        specgram_type=args.specgram_type,
+        num_threads=args.num_threads_data)
     train_batch_reader = train_generator.batch_reader_creator(
         manifest_path=args.train_manifest_path,
         batch_size=args.batch_size,
         min_batch_size=args.trainer_count,
         sortagrad=args.use_sortagrad if args.init_model_path is None else False,
         shuffle_method=args.shuffle_method)
-    test_batch_reader = test_generator.batch_reader_creator(
+    dev_batch_reader = dev_generator.batch_reader_creator(
         manifest_path=args.dev_manifest_path,
         batch_size=args.batch_size,
         min_batch_size=1,  # must be 1, but will have errors.
         sortagrad=False,
         shuffle_method=None)
 
-    # create event handler
-    def event_handler(event):
-        global start_time, cost_sum, cost_counter
-        if isinstance(event, paddle.event.EndIteration):
-            cost_sum += event.cost
-            cost_counter += 1
-            if (event.batch_id + 1) % 100 == 0:
-                print("\nPass: %d, Batch: %d, TrainCost: %f" % (
-                    event.pass_id, event.batch_id + 1, cost_sum / cost_counter))
-                cost_sum, cost_counter = 0.0, 0
-                with gzip.open("checkpoints/params.latest.tar.gz", 'w') as f:
-                    parameters.to_tar(f)
-            else:
-                sys.stdout.write('.')
-                sys.stdout.flush()
-        if isinstance(event, paddle.event.BeginPass):
-            start_time = time.time()
-            cost_sum, cost_counter = 0.0, 0
-        if isinstance(event, paddle.event.EndPass):
-            result = trainer.test(
-                reader=test_batch_reader, feeding=test_generator.feeding)
-            print("\n------- Time: %d sec,  Pass: %d, ValidationCost: %s" %
-                  (time.time() - start_time, event.pass_id, result.cost))
-            with gzip.open("checkpoints/params.pass-%d.tar.gz" % event.pass_id,
-                           'w') as f:
-                parameters.to_tar(f)
-
-    # run train
-    trainer.train(
-        reader=train_batch_reader,
-        event_handler=event_handler,
+    ds2_model = DeepSpeech2Model(
+        vocab_size=train_generator.vocab_size,
+        num_conv_layers=args.num_conv_layers,
+        num_rnn_layers=args.num_rnn_layers,
+        rnn_layer_size=args.rnn_layer_size,
+        pretrained_model_path=args.init_model_path)
+    ds2_model.train(
+        train_batch_reader=train_batch_reader,
+        dev_batch_reader=dev_batch_reader,
+        feeding_dict=train_generator.feeding,
+        learning_rate=args.adam_learning_rate,
+        gradient_clipping=400,
         num_passes=args.num_passes,
-        feeding=train_generator.feeding)
+        num_iterations_print=args.num_iterations_print,
+        output_model_dir=args.output_model_dir)
 
 
 def main():

tune.py

@@ -3,14 +3,13 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import numpy as np
 import distutils.util
 import argparse
-import gzip
+import multiprocessing
 import paddle.v2 as paddle
 from data_utils.data import DataGenerator
-from model import deep_speech2
-from decoder import *
-from lm.lm_scorer import LmScorer
+from model import DeepSpeech2Model
 from error_rate import wer
 import utils
 
@@ -40,14 +39,19 @@ parser.add_argument(
     default=True,
     type=distutils.util.strtobool,
     help="Use gpu or not. (default: %(default)s)")
+parser.add_argument(
+    "--trainer_count",
+    default=8,
+    type=int,
+    help="Trainer number. (default: %(default)s)")
 parser.add_argument(
     "--num_threads_data",
-    default=multiprocessing.cpu_count(),
+    default=1,
     type=int,
     help="Number of cpu threads for preprocessing data. (default: %(default)s)")
 parser.add_argument(
     "--num_processes_beam_search",
-    default=multiprocessing.cpu_count(),
+    default=multiprocessing.cpu_count() // 2,
     type=int,
     help="Number of cpu processes for beam search. (default: %(default)s)")
 parser.add_argument(
@@ -62,10 +66,10 @@ parser.add_argument(
     type=str,
     help="Manifest path for normalizer. (default: %(default)s)")
 parser.add_argument(
-    "--decode_manifest_path",
-    default='datasets/manifest.test',
+    "--tune_manifest_path",
+    default='datasets/manifest.dev',
     type=str,
-    help="Manifest path for decoding. (default: %(default)s)")
+    help="Manifest path for tuning. (default: %(default)s)")
 parser.add_argument(
     "--model_filepath",
     default='checkpoints/params.latest.tar.gz',
@@ -127,96 +131,64 @@ args = parser.parse_args()
 
 def tune():
     """Tune parameters alpha and beta on one minibatch."""
-
     if not args.num_alphas >= 0:
         raise ValueError("num_alphas must be non-negative!")
-
     if not args.num_betas >= 0:
         raise ValueError("num_betas must be non-negative!")
 
-    # initialize data generator
     data_generator = DataGenerator(
         vocab_filepath=args.vocab_filepath,
         mean_std_filepath=args.mean_std_filepath,
         augmentation_config='{}',
         specgram_type=args.specgram_type,
         num_threads=args.num_threads_data)
-
-    # create network config
-    # paddle.data_type.dense_array is used for variable batch input.
-    # The size 161 * 161 is only an placeholder value and the real shape
-    # of input batch data will be induced during training.
-    audio_data = paddle.layer.data(
-        name="audio_spectrogram", type=paddle.data_type.dense_array(161 * 161))
-    text_data = paddle.layer.data(
-        name="transcript_text",
-        type=paddle.data_type.integer_value_sequence(data_generator.vocab_size))
-    output_probs = deep_speech2(
-        audio_data=audio_data,
-        text_data=text_data,
-        dict_size=data_generator.vocab_size,
-        num_conv_layers=args.num_conv_layers,
-        num_rnn_layers=args.num_rnn_layers,
-        rnn_size=args.rnn_layer_size,
-        is_inference=True)
-
-    # load parameters
-    parameters = paddle.parameters.Parameters.from_tar(
-        gzip.open(args.model_filepath))
-
-    # prepare infer data
     batch_reader = data_generator.batch_reader_creator(
-        manifest_path=args.decode_manifest_path,
+        manifest_path=args.tune_manifest_path,
         batch_size=args.num_samples,
         sortagrad=False,
         shuffle_method=None)
-    # get one batch data for tuning
-    infer_data = batch_reader().next()
-
-    # run inference
-    infer_results = paddle.infer(
-        output_layer=output_probs, parameters=parameters, input=infer_data)
-    num_steps = len(infer_results) // len(infer_data)
-    probs_split = [
-        infer_results[i * num_steps:(i + 1) * num_steps]
-        for i in xrange(0, len(infer_data))
+    tune_data = batch_reader().next()
+    target_transcripts = [
+        ''.join([data_generator.vocab_list[token] for token in transcript])
+        for _, transcript in tune_data
     ]
 
+    ds2_model = DeepSpeech2Model(
+        vocab_size=data_generator.vocab_size,
+        num_conv_layers=args.num_conv_layers,
+        num_rnn_layers=args.num_rnn_layers,
+        rnn_layer_size=args.rnn_layer_size,
+        pretrained_model_path=args.model_filepath)
+
     # create grid for search
     cand_alphas = np.linspace(args.alpha_from, args.alpha_to, args.num_alphas)
     cand_betas = np.linspace(args.beta_from, args.beta_to, args.num_betas)
     params_grid = [(alpha, beta) for alpha in cand_alphas
                    for beta in cand_betas]
 
-    ext_scorer = LmScorer(args.alpha_from, args.beta_from,
-                          args.language_model_path)
     ## tune parameters in loop
     for alpha, beta in params_grid:
-        wer_sum, wer_counter = 0, 0
-        # reset scorer
-        ext_scorer.reset_params(alpha, beta)
-        # beam search using multiple processes
-        beam_search_results = ctc_beam_search_decoder_batch(
-            probs_split=probs_split,
-            vocabulary=data_generator.vocab_list,
+        result_transcripts = ds2_model.infer_batch(
+            infer_data=tune_data,
+            decode_method='beam_search',
+            beam_alpha=alpha,
+            beam_beta=beta,
             beam_size=args.beam_size,
             cutoff_prob=args.cutoff_prob,
-            blank_id=len(data_generator.vocab_list),
-            num_processes=args.num_processes_beam_search,
-            ext_scoring_func=ext_scorer, )
-        for i, beam_search_result in enumerate(beam_search_results):
-            target_transcription = ''.join([
-                data_generator.vocab_list[index] for index in infer_data[i][1]
-            ])
-            wer_sum += wer(target_transcription, beam_search_result[0][1])
-            wer_counter += 1
-
+            vocab_list=data_generator.vocab_list,
+            language_model_path=args.language_model_path,
+            num_processes=args.num_processes_beam_search)
+        wer_sum, num_ins = 0.0, 0
+        for target, result in zip(target_transcripts, result_transcripts):
+            wer_sum += wer(target, result)
+            num_ins += 1
         print("alpha = %f\tbeta = %f\tWER = %f" %
-              (alpha, beta, wer_sum / wer_counter))
+              (alpha, beta, wer_sum / num_ins))
 
 
 def main():
-    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    utils.print_arguments(args)
+    paddle.init(use_gpu=args.use_gpu, trainer_count=args.trainer_count)
     tune()