Merge branch 'develop' into ctc_decoder_deploy

deep_speech_2/README.md

@@ -77,3 +77,29 @@ More help for arguments:
 ```
 python infer.py --help
 ```
+
+### Evaluating
+
+```
+CUDA_VISIBLE_DEVICES=0 python evaluate.py
+```
+
+More help for arguments:
+
+```
+python evaluate.py --help
+```
+
+### Parameters tuning
+
+Parameters tuning for the CTC beam search decoder
+
+```
+CUDA_VISIBLE_DEVICES=0 python tune.py
+```
+
+More help for arguments:
+
+```
+python tune.py --help
+```

deep_speech_2/decoder.py

-"""Contains various CTC decoder."""
+"""Contains various CTC decoders."""
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
-import numpy as np
 from itertools import groupby
+import numpy as np
+from math import log
+import multiprocessing
 
 
-def ctc_best_path_decode(probs_seq, vocabulary):
-    """Best path decoding, also called argmax decoding or greedy decoding.
+def ctc_best_path_decoder(probs_seq, vocabulary):
+    """Best path decoder, also called argmax decoder or greedy decoder.
     Path consisting of the most probable tokens are further post-processed to
     remove consecutive repetitions and all blanks.
 
@@ -36,24 +38,200 @@ def ctc_best_path_decode(probs_seq, vocabulary):
     return ''.join([vocabulary[index] for index in index_list])
 
 
-def ctc_decode(probs_seq, vocabulary, method):
-    """CTC-like sequence decoding from a sequence of likelihood probablilites.
+def ctc_beam_search_decoder(probs_seq,
+                            beam_size,
+                            vocabulary,
+                            blank_id,
+                            cutoff_prob=1.0,
+                            ext_scoring_func=None,
+                            nproc=False):
+    """Beam search decoder for CTC-trained network. It utilizes beam search
+    to approximately select top best decoding labels and returning results
+    in the descending order. The implementation is based on Prefix
+    Beam Search (https://arxiv.org/abs/1408.2873), and the unclear part is
+    redesigned. Two important modifications: 1) in the iterative computation
+    of probabilities, the assignment operation is changed to accumulation for
+    one prefix may comes from different paths; 2) the if condition "if l^+ not
+    in A_prev then" after probabilities' computation is deprecated for it is
+    hard to understand and seems unnecessary.
 
-    :param probs_seq: 2-D list of probabilities over the vocabulary for each
-                      character. Each element is a list of float probabilities
-                      for one character.
-    :type probs_seq: list
+    :param probs_seq: 2-D list of probability distributions over each time
+                      step, with each element being a list of normalized
+                      probabilities over vocabulary and blank.
+    :type probs_seq: 2-D list
+    :param beam_size: Width for beam search.
+    :type beam_size: int
     :param vocabulary: Vocabulary list.
     :type vocabulary: list
-    :param method: Decoding method name, with options: "best_path".
-    :type method: basestring
-    :return: Decoding result string.
-    :rtype: baseline
+    :param blank_id: ID of blank.
+    :type blank_id: int
+    :param cutoff_prob: Cutoff probability in pruning,
+                        default 1.0, no pruning.
+    :type cutoff_prob: float
+    :param ext_scoring_func: External scoring function for
+                            partially decoded sentence, e.g. word count
+                            or language model.
+    :type external_scoring_func: callable
+    :param nproc: Whether the decoder used in multiprocesses.
+    :type nproc: bool
+    :return: List of tuples of log probability and sentence as decoding
+             results, in descending order of the probability.
+    :rtype: list
     """
+    # dimension check
     for prob_list in probs_seq:
         if not len(prob_list) == len(vocabulary) + 1:
-            raise ValueError("probs dimension mismatchedd with vocabulary")
-    if method == "best_path":
-        return ctc_best_path_decode(probs_seq, vocabulary)
-    else:
-        raise ValueError("Decoding method [%s] is not supported.")
+            raise ValueError("The shape of prob_seq does not match with the "
+                             "shape of the vocabulary.")
+
+    # blank_id check
+    if not blank_id < len(probs_seq[0]):
+        raise ValueError("blank_id shouldn't be greater than probs dimension")
+
+    # If the decoder called in the multiprocesses, then use the global scorer
+    # instantiated in ctc_beam_search_decoder_batch().
+    if nproc is True:
+        global ext_nproc_scorer
+        ext_scoring_func = ext_nproc_scorer
+
+    ## initialize
+    # prefix_set_prev: the set containing selected prefixes
+    # probs_b_prev: prefixes' probability ending with blank in previous step
+    # probs_nb_prev: prefixes' probability ending with non-blank in previous step
+    prefix_set_prev = {'\t': 1.0}
+    probs_b_prev, probs_nb_prev = {'\t': 1.0}, {'\t': 0.0}
+
+    ## extend prefix in loop
+    for time_step in xrange(len(probs_seq)):
+        # prefix_set_next: the set containing candidate prefixes
+        # probs_b_cur: prefixes' probability ending with blank in current step
+        # probs_nb_cur: prefixes' probability ending with non-blank in current step
+        prefix_set_next, probs_b_cur, probs_nb_cur = {}, {}, {}
+
+        prob_idx = list(enumerate(probs_seq[time_step]))
+        cutoff_len = len(prob_idx)
+        #If pruning is enabled
+        if cutoff_prob < 1.0:
+            prob_idx = sorted(prob_idx, key=lambda asd: asd[1], reverse=True)
+            cutoff_len, cum_prob = 0, 0.0
+            for i in xrange(len(prob_idx)):
+                cum_prob += prob_idx[i][1]
+                cutoff_len += 1
+                if cum_prob >= cutoff_prob:
+                    break
+            prob_idx = prob_idx[0:cutoff_len]
+
+        for l in prefix_set_prev:
+            if not prefix_set_next.has_key(l):
+                probs_b_cur[l], probs_nb_cur[l] = 0.0, 0.0
+
+            # extend prefix by travering prob_idx
+            for index in xrange(cutoff_len):
+                c, prob_c = prob_idx[index][0], prob_idx[index][1]
+
+                if c == blank_id:
+                    probs_b_cur[l] += prob_c * (
+                        probs_b_prev[l] + probs_nb_prev[l])
+                else:
+                    last_char = l[-1]
+                    new_char = vocabulary[c]
+                    l_plus = l + new_char
+                    if not prefix_set_next.has_key(l_plus):
+                        probs_b_cur[l_plus], probs_nb_cur[l_plus] = 0.0, 0.0
+
+                    if new_char == last_char:
+                        probs_nb_cur[l_plus] += prob_c * probs_b_prev[l]
+                        probs_nb_cur[l] += prob_c * probs_nb_prev[l]
+                    elif new_char == ' ':
+                        if (ext_scoring_func is None) or (len(l) == 1):
+                            score = 1.0
+                        else:
+                            prefix = l[1:]
+                            score = ext_scoring_func(prefix)
+                        probs_nb_cur[l_plus] += score * prob_c * (
+                            probs_b_prev[l] + probs_nb_prev[l])
+                    else:
+                        probs_nb_cur[l_plus] += prob_c * (
+                            probs_b_prev[l] + probs_nb_prev[l])
+                    # add l_plus into prefix_set_next
+                    prefix_set_next[l_plus] = probs_nb_cur[
+                        l_plus] + probs_b_cur[l_plus]
+            # add l into prefix_set_next
+            prefix_set_next[l] = probs_b_cur[l] + probs_nb_cur[l]
+        # update probs
+        probs_b_prev, probs_nb_prev = probs_b_cur, probs_nb_cur
+
+        ## store top beam_size prefixes
+        prefix_set_prev = sorted(
+            prefix_set_next.iteritems(), key=lambda asd: asd[1], reverse=True)
+        if beam_size < len(prefix_set_prev):
+            prefix_set_prev = prefix_set_prev[:beam_size]
+        prefix_set_prev = dict(prefix_set_prev)
+
+    beam_result = []
+    for seq, prob in prefix_set_prev.items():
+        if prob > 0.0 and len(seq) > 1:
+            result = seq[1:]
+            # score last word by external scorer
+            if (ext_scoring_func is not None) and (result[-1] != ' '):
+                prob = prob * ext_scoring_func(result)
+            log_prob = log(prob)
+            beam_result.append((log_prob, result))
+
+    ## output top beam_size decoding results
+    beam_result = sorted(beam_result, key=lambda asd: asd[0], reverse=True)
+    return beam_result
+
+
+def ctc_beam_search_decoder_batch(probs_split,
+                                  beam_size,
+                                  vocabulary,
+                                  blank_id,
+                                  num_processes,
+                                  cutoff_prob=1.0,
+                                  ext_scoring_func=None):
+    """CTC beam search decoder using multiple processes.
+
+    :param probs_seq: 3-D list with each element as an instance of 2-D list
+                      of probabilities used by ctc_beam_search_decoder().
+    :type probs_seq: 3-D list
+    :param beam_size: Width for beam search.
+    :type beam_size: int
+    :param vocabulary: Vocabulary list.
+    :type vocabulary: list
+    :param blank_id: ID of blank.
+    :type blank_id: int
+    :param num_processes: Number of parallel processes.
+    :type num_processes: int
+    :param cutoff_prob: Cutoff probability in pruning,
+                        default 1.0, no pruning.
+    :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.
+    :type external_scoring_function: callable
+    :return: List of tuples of log probability and sentence as decoding
+             results, in descending order of the probability.
+    :rtype: list
+    """
+    if not num_processes > 0:
+        raise ValueError("Number of processes must be positive!")
+
+    # use global variable to pass the externnal scorer to beam search decoder
+    global ext_nproc_scorer
+    ext_nproc_scorer = ext_scoring_func
+    nproc = True
+
+    pool = multiprocessing.Pool(processes=num_processes)
+    results = []
+    for i, probs_list in enumerate(probs_split):
+        args = (probs_list, beam_size, vocabulary, blank_id, cutoff_prob, None,
+                nproc)
+        results.append(pool.apply_async(ctc_beam_search_decoder, args))
+
+    pool.close()
+    pool.join()
+    beam_search_results = [result.get() for result in results]
+    return beam_search_results

deep_speech_2/evaluate.py

+"""Evaluation for DeepSpeech2 model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import distutils.util
+import argparse
+import gzip
+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
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--batch_size",
+    default=100,
+    type=int,
+    help="Minibatch size for evaluation. (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(
+    "--num_threads_data",
+    default=multiprocessing.cpu_count(),
+    type=int,
+    help="Number of cpu threads for preprocessing data. (default: %(default)s)")
+parser.add_argument(
+    "--num_processes_beam_search",
+    default=multiprocessing.cpu_count(),
+    type=int,
+    help="Number of cpu processes for beam search. (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(
+    "--decode_method",
+    default='beam_search',
+    type=str,
+    help="Method for ctc decoding, best_path or beam_search. (default: %(default)s)"
+)
+parser.add_argument(
+    "--language_model_path",
+    default="lm/data/1Billion.klm",
+    type=str,
+    help="Path for language model. (default: %(default)s)")
+parser.add_argument(
+    "--alpha",
+    default=0.26,
+    type=float,
+    help="Parameter associated with language model. (default: %(default)f)")
+parser.add_argument(
+    "--beta",
+    default=0.1,
+    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)")
+parser.add_argument(
+    "--beam_size",
+    default=500,
+    type=int,
+    help="Width for beam search decoding. (default: %(default)d)")
+parser.add_argument(
+    "--decode_manifest_path",
+    default='datasets/manifest.test',
+    type=str,
+    help="Manifest path for decoding. (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(
+    "--vocab_filepath",
+    default='datasets/vocab/eng_vocab.txt',
+    type=str,
+    help="Vocabulary filepath. (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='{}',
+        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,
+        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)
+
+    wer_counter, wer_sum = 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)
+        ]
+        # 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))
+
+
+def main():
+    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    evaluate()
+
+
+if __name__ == '__main__':
+    main()

deep_speech_2/infer.py

@@ -10,7 +10,9 @@ import multiprocessing
 import paddle.v2 as paddle
 from data_utils.data import DataGenerator
 from model import deep_speech2
-from decoder import ctc_decode
+from decoder import *
+from lm.lm_scorer import LmScorer
+from error_rate import wer
 import utils
 
 parser = argparse.ArgumentParser(description=__doc__)
@@ -44,6 +46,11 @@ parser.add_argument(
     default=multiprocessing.cpu_count(),
     type=int,
     help="Number of cpu threads for preprocessing data. (default: %(default)s)")
+parser.add_argument(
+    "--num_processes_beam_search",
+    default=multiprocessing.cpu_count(),
+    type=int,
+    help="Number of cpu processes for beam search. (default: %(default)s)")
 parser.add_argument(
     "--mean_std_filepath",
     default='mean_std.npz',
@@ -64,11 +71,48 @@ parser.add_argument(
     default='datasets/vocab/eng_vocab.txt',
     type=str,
     help="Vocabulary 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=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/1Billion.klm",
+    type=str,
+    help="Path for language model. (default: %(default)s)")
+parser.add_argument(
+    "--alpha",
+    default=0.26,
+    type=float,
+    help="Parameter associated with language model. (default: %(default)f)")
+parser.add_argument(
+    "--beta",
+    default=0.1,
+    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()
 
 
 def infer():
-    """Max-ctc-decoding for DeepSpeech2."""
+    """Inference for DeepSpeech2."""
     # initialize data generator
     data_generator = DataGenerator(
         vocab_filepath=args.vocab_filepath,
@@ -102,6 +146,7 @@ def infer():
     batch_reader = data_generator.batch_reader_creator(
         manifest_path=args.decode_manifest_path,
         batch_size=args.num_samples,
+        min_batch_size=1,
         sortagrad=False,
         shuffle_method=None)
     infer_data = batch_reader().next()
@@ -115,16 +160,52 @@ def infer():
         for i in xrange(len(infer_data))
     ]
 
-    # decode and print
-    for i, probs in enumerate(probs_split):
-        output_transcription = ctc_decode(
-            probs_seq=probs,
-            vocabulary=data_generator.vocab_list,
-            method="best_path")
-        target_transcription = ''.join(
+    # targe transcription
+    target_transcription = [
+        ''.join(
             [data_generator.vocab_list[index] for index in infer_data[i][1]])
-        print("Target Transcription: %s \nOutput Transcription: %s \n" %
-              (target_transcription, output_transcription))
+        for i, probs in enumerate(probs_split)
+    ]
+
+    ## 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)
 
 
 def main():

deep_speech_2/lm/lm_scorer.py

+"""External Scorer for Beam Search Decoder."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import kenlm
+import numpy as np
+
+
+class LmScorer(object):
+    """External scorer to evaluate a prefix or whole sentence in
+       beam search decoding, including the score from n-gram language
+       model and word count.
+
+    :param alpha: Parameter associated with language model. Don't use
+                  language model when alpha = 0.
+    :type alpha: float
+    :param beta: Parameter associated with word count. Don't use word
+                count when beta = 0.
+    :type beta: float
+    :model_path: Path to load language model.
+    :type model_path: basestring
+    """
+
+    def __init__(self, alpha, beta, model_path):
+        self._alpha = alpha
+        self._beta = beta
+        if not os.path.isfile(model_path):
+            raise IOError("Invaid language model path: %s" % model_path)
+        self._language_model = kenlm.LanguageModel(model_path)
+
+    # n-gram language model scoring
+    def _language_model_score(self, sentence):
+        #log10 prob of last word
+        log_cond_prob = list(
+            self._language_model.full_scores(sentence, eos=False))[-1][0]
+        return np.power(10, log_cond_prob)
+
+    # word insertion term
+    def _word_count(self, sentence):
+        words = sentence.strip().split(' ')
+        return len(words)
+
+    # reset alpha and beta
+    def reset_params(self, alpha, beta):
+        self._alpha = alpha
+        self._beta = beta
+
+    # execute evaluation
+    def __call__(self, sentence, log=False):
+        """Evaluation function, gathering all the different scores
+        and return the final one.
+
+        :param sentence: The input sentence for evalutation
+        :type sentence: basestring
+        :param log: Whether return the score in log representation.
+        :type log: bool
+        :return: Evaluation score, in the decimal or log.
+        :rtype: float
+        """
+        lm = self._language_model_score(sentence)
+        word_cnt = self._word_count(sentence)
+        if log == False:
+            score = np.power(lm, self._alpha) * np.power(word_cnt, self._beta)
+        else:
+            score = self._alpha * np.log(lm) + self._beta * np.log(word_cnt)
+        return score

deep_speech_2/lm/run.sh

+echo "Downloading language model."
+
+wget -c ftp://xxx/xxx/en.00.UNKNOWN.klm -P ./data

deep_speech_2/requirements.txt

 wget==3.2
 scipy==0.13.1
-resampy==0.1.5
\ No newline at end of file
+resampy==0.1.5
+https://github.com/kpu/kenlm/archive/master.zip

deep_speech_2/tests/test_decoders.py

+"""Test decoders."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import unittest
+from decoder import *
+
+
+class TestDecoders(unittest.TestCase):
+    def setUp(self):
+        self.vocab_list = ["\'", ' ', 'a', 'b', 'c', 'd']
+        self.beam_size = 20
+        self.probs_seq1 = [[
+            0.06390443, 0.21124858, 0.27323887, 0.06870235, 0.0361254,
+            0.18184413, 0.16493624
+        ], [
+            0.03309247, 0.22866108, 0.24390638, 0.09699597, 0.31895462,
+            0.0094893, 0.06890021
+        ], [
+            0.218104, 0.19992557, 0.18245131, 0.08503348, 0.14903535,
+            0.08424043, 0.08120984
+        ], [
+            0.12094152, 0.19162472, 0.01473646, 0.28045061, 0.24246305,
+            0.05206269, 0.09772094
+        ], [
+            0.1333387, 0.00550838, 0.00301669, 0.21745861, 0.20803985,
+            0.41317442, 0.01946335
+        ], [
+            0.16468227, 0.1980699, 0.1906545, 0.18963251, 0.19860937,
+            0.04377724, 0.01457421
+        ]]
+        self.probs_seq2 = [[
+            0.08034842, 0.22671944, 0.05799633, 0.36814645, 0.11307441,
+            0.04468023, 0.10903471
+        ], [
+            0.09742457, 0.12959763, 0.09435383, 0.21889204, 0.15113123,
+            0.10219457, 0.20640612
+        ], [
+            0.45033529, 0.09091417, 0.15333208, 0.07939558, 0.08649316,
+            0.12298585, 0.01654384
+        ], [
+            0.02512238, 0.22079203, 0.19664364, 0.11906379, 0.07816055,
+            0.22538587, 0.13483174
+        ], [
+            0.17928453, 0.06065261, 0.41153005, 0.1172041, 0.11880313,
+            0.07113197, 0.04139363
+        ], [
+            0.15882358, 0.1235788, 0.23376776, 0.20510435, 0.00279306,
+            0.05294827, 0.22298418
+        ]]
+        self.best_path_result = ["ac'bdc", "b'da"]
+        self.beam_search_result = ['acdc', "b'a"]
+
+    def test_best_path_decoder_1(self):
+        bst_result = ctc_best_path_decoder(self.probs_seq1, self.vocab_list)
+        self.assertEqual(bst_result, self.best_path_result[0])
+
+    def test_best_path_decoder_2(self):
+        bst_result = ctc_best_path_decoder(self.probs_seq2, self.vocab_list)
+        self.assertEqual(bst_result, self.best_path_result[1])
+
+    def test_beam_search_decoder_1(self):
+        beam_result = ctc_beam_search_decoder(
+            probs_seq=self.probs_seq1,
+            beam_size=self.beam_size,
+            vocabulary=self.vocab_list,
+            blank_id=len(self.vocab_list))
+        self.assertEqual(beam_result[0][1], self.beam_search_result[0])
+
+    def test_beam_search_decoder_2(self):
+        beam_result = ctc_beam_search_decoder(
+            probs_seq=self.probs_seq2,
+            beam_size=self.beam_size,
+            vocabulary=self.vocab_list,
+            blank_id=len(self.vocab_list))
+        self.assertEqual(beam_result[0][1], self.beam_search_result[1])
+
+    def test_beam_search_decoder_batch(self):
+        beam_results = ctc_beam_search_decoder_batch(
+            probs_split=[self.probs_seq1, self.probs_seq2],
+            beam_size=self.beam_size,
+            vocabulary=self.vocab_list,
+            blank_id=len(self.vocab_list),
+            num_processes=24)
+        self.assertEqual(beam_results[0][0][1], self.beam_search_result[0])
+        self.assertEqual(beam_results[1][0][1], self.beam_search_result[1])
+
+
+if __name__ == '__main__':
+    unittest.main()

deep_speech_2/tune.py

+"""Parameters tuning for DeepSpeech2 model."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import distutils.util
+import argparse
+import gzip
+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
+import utils
+
+parser = argparse.ArgumentParser(description=__doc__)
+parser.add_argument(
+    "--num_samples",
+    default=100,
+    type=int,
+    help="Number of samples for parameters tuning. (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(
+    "--num_threads_data",
+    default=multiprocessing.cpu_count(),
+    type=int,
+    help="Number of cpu threads for preprocessing data. (default: %(default)s)")
+parser.add_argument(
+    "--num_processes_beam_search",
+    default=multiprocessing.cpu_count(),
+    type=int,
+    help="Number of cpu processes for beam search. (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(
+    "--decode_manifest_path",
+    default='datasets/manifest.test',
+    type=str,
+    help="Manifest path for decoding. (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(
+    "--vocab_filepath",
+    default='datasets/vocab/eng_vocab.txt',
+    type=str,
+    help="Vocabulary filepath. (default: %(default)s)")
+parser.add_argument(
+    "--beam_size",
+    default=500,
+    type=int,
+    help="Width for beam search decoding. (default: %(default)d)")
+parser.add_argument(
+    "--language_model_path",
+    default="lm/data/1Billion.klm",
+    type=str,
+    help="Path for language model. (default: %(default)s)")
+parser.add_argument(
+    "--alpha_from",
+    default=0.1,
+    type=float,
+    help="Where alpha starts from. (default: %(default)f)")
+parser.add_argument(
+    "--num_alphas",
+    default=14,
+    type=int,
+    help="Number of candidate alphas. (default: %(default)d)")
+parser.add_argument(
+    "--alpha_to",
+    default=0.36,
+    type=float,
+    help="Where alpha ends with. (default: %(default)f)")
+parser.add_argument(
+    "--beta_from",
+    default=0.05,
+    type=float,
+    help="Where beta starts from. (default: %(default)f)")
+parser.add_argument(
+    "--num_betas",
+    default=20,
+    type=float,
+    help="Number of candidate betas. (default: %(default)d)")
+parser.add_argument(
+    "--beta_to",
+    default=1.0,
+    type=float,
+    help="Where beta ends with. (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()
+
+
+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='{}',
+        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,
+        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))
+    ]
+
+    # 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,
+            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
+
+        print("alpha = %f\tbeta = %f\tWER = %f" %
+              (alpha, beta, wer_sum / wer_counter))
+
+
+def main():
+    paddle.init(use_gpu=args.use_gpu, trainer_count=1)
+    tune()
+
+
+if __name__ == '__main__':
+    main()

image_classification/caffe2paddle/caffe2paddle.py

@@ -72,6 +72,10 @@ class ModelConverter(object):
                 file_name = "_%s.w%s" % (name, str(i))
             param_conf = ParameterConfig()
             param_conf.name = file_name
+            dims = list(data.shape)
+            if len(dims) == 1:
+                dims.insert(1, 1)
+                param_conf.dims.extend(dims)
             param_conf.size = reduce(lambda a, b: a * b, data.shape)
             self.params[file_name] = (param_conf, data.flatten())