remove unuseful code, test=doc

demos/speech_recognition/run.sh

-#!/bin/bash
-
-# wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
-
-# asr
-export CUDA_VISIBLE_DEVICES=0
-paddlespeech asr --input audio/119994.wav -v
-
-
-# asr + punc
-# paddlespeech asr --input ./zh.wav | paddlespeech text --task punc
\ No newline at end of file

examples/aishell/asr1/conf/preprocess.yaml

@@ -5,7 +5,7 @@ process:
     n_mels: 80
     n_shift: 160
     win_length: 400
-    dither: 0.0
+    dither: 0.1
   - type: cmvn_json
     cmvn_path: data/mean_std.json
   # these three processes are a.k.a. SpecAugument

examples/aishell/asr1/conf/tuning/decode.yaml

@@ -3,9 +3,9 @@ decode_batch_size: 128
 error_rate_type: cer 
 decoding_method: attention # 'attention', 'ctc_greedy_search', 'ctc_prefix_beam_search', 'attention_rescoring'
 ctc_weight: 0.5 # ctc weight for attention rescoring decode mode.
-decoding_chunk_size: 1 # decoding chunk size. Defaults to -1.
+decoding_chunk_size: -1 # decoding chunk size. Defaults to -1.
     # <0: for decoding, use full chunk.
     # >0: for decoding, use fixed chunk size as set.
     # 0: used for training, it's prohibited here. 
 num_decoding_left_chunks: -1  # number of left chunks for decoding. Defaults to -1.
-simulate_streaming: True  # simulate streaming inference. Defaults to False.
+simulate_streaming: False  # simulate streaming inference. Defaults to False.

examples/aishell/asr1/run.sh

@@ -3,12 +3,12 @@ source path.sh
 set -e
 
 gpus=0,1,2,3
-stage=5
-stop_stage=5
-conf_path=conf/chunk_conformer.yaml
+stage=0
+stop_stage=50
+conf_path=conf/conformer.yaml
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=20
-audio_file=audio/zh.wav
+audio_file=data/demo_01_03.wav
 
 source ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
 
@@ -44,7 +44,7 @@ fi
 # Optionally, you can add LM and test it with runtime.
 if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
     # test a single .wav file
-    CUDA_VISIBLE_DEVICES=0 ./local/test_wav.sh ${conf_path} ${decode_conf_path} exp/chunk_conformer/checkpoints/multi_cn ${audio_file} || exit -1
+    CUDA_VISIBLE_DEVICES=0 ./local/test_wav.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} ${audio_file} || exit -1
 fi
 
 # Not supported at now!!!

paddlespeech/__init__.py

@@ -14,6 +14,3 @@
 import _locale
 
 _locale._getdefaultlocale = (lambda *args: ['en_US', 'utf8'])
-
-
-

paddlespeech/s2t/exps/u2/bin/test_wav.py

@@ -128,12 +128,10 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     config = CfgNode(new_allowed=True)
-    
+
     if args.config:
-        print(f"load config: {args.config}")
         config.merge_from_file(args.config)
     if args.decode_cfg:
-        print(f"load decode cfg: {args.decode_cfg}")
         decode_confs = CfgNode(new_allowed=True)
         decode_confs.merge_from_file(args.decode_cfg)
         config.decode = decode_confs

paddlespeech/server/conf/ws_application.yaml

@@ -4,7 +4,7 @@
 #                             SERVER SETTING                                    #
 #################################################################################
 host: 0.0.0.0
-port: 8096
+port: 8090
 
 # The task format in the engin_list is: <speech task>_<engine type>
 # task choices = ['asr_online', 'tts_online']

paddlespeech/server/tests/asr/online/websocket_client.py

@@ -105,7 +105,7 @@ class ASRAudioHandler:
 def main(args):
     logging.basicConfig(level=logging.INFO)
     logging.info("asr websocket client start")
-    handler = ASRAudioHandler("127.0.0.1", 8096)
+    handler = ASRAudioHandler("127.0.0.1", 8090)
     loop = asyncio.get_event_loop()
 
     # support to process single audio file

paddlespeech/server/ws/asr_socket.py

@@ -93,7 +93,6 @@ async def websocket_endpoint(websocket: WebSocket):
                     sample_rate = asr_engine.config.sample_rate
                     x_chunk, x_chunk_lens = asr_engine.preprocess(samples,
                                                                   sample_rate)
-                    print(x_chunk_lens)
                     asr_engine.run(x_chunk, x_chunk_lens)
                     asr_results = asr_engine.postprocess()
                 asr_results = asr_engine.postprocess()

paddlespeech/vector/cluster/diarization.py

@@ -18,11 +18,11 @@ A few sklearn functions are modified in this script as per requirement.
 """
 import argparse
 import warnings
+from distutils.util import strtobool
 
 import numpy as np
 import scipy
 import sklearn
-from distutils.util import strtobool
 from scipy import sparse
 from scipy.sparse.csgraph import connected_components
 from scipy.sparse.csgraph import laplacian as csgraph_laplacian

setup.py

@@ -168,7 +168,7 @@ class DevelopCommand(develop):
     def run(self):
         develop.run(self)
         # must after develop.run, or pkg install by shell will not see
-    #    self.execute(_post_install, (self.install_lib, ), msg="Post Install...")
+        self.execute(_post_install, (self.install_lib, ), msg="Post Install...")
 
 
 class InstallCommand(install):

utils/DER.py

@@ -26,9 +26,9 @@ import argparse
 import os
 import re
 import subprocess
+from distutils.util import strtobool
 
 import numpy as np
-from distutils.util import strtobool
 
 FILE_IDS = re.compile(r"(?<=Speaker Diarization for).+(?=\*\*\*)")
 SCORED_SPEAKER_TIME = re.compile(r"(?<=SCORED SPEAKER TIME =)[\d.]+")