From efc269b75f0ef8b9739d159aea84e3e1423a8a4a Mon Sep 17 00:00:00 2001
From: xiongxinlei <xiongxinlei@baidu.com>
Date: Sat, 16 Apr 2022 15:03:25 +0800
Subject: [PATCH] remove unuseful code, test=doc
---
demos/speech_recognition/run.sh | 11 -----------
examples/aishell/asr1/conf/preprocess.yaml | 2 +-
examples/aishell/asr1/conf/tuning/decode.yaml | 4 ++--
examples/aishell/asr1/run.sh | 10 +++++-----
paddlespeech/__init__.py | 3 ---
paddlespeech/s2t/exps/u2/bin/test_wav.py | 4 +---
paddlespeech/server/conf/ws_application.yaml | 2 +-
.../server/tests/asr/online/websocket_client.py | 2 +-
paddlespeech/server/ws/asr_socket.py | 1 -
paddlespeech/vector/cluster/diarization.py | 2 +-
setup.py | 2 +-
utils/DER.py | 2 +-
12 files changed, 14 insertions(+), 31 deletions(-)
delete mode 100755 demos/speech_recognition/run.sh
diff --git a/demos/speech_recognition/run.sh b/demos/speech_recognition/run.sh
deleted file mode 100755
index a9ae937d2..000000000
--- a/demos/speech_recognition/run.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/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
diff --git a/examples/aishell/asr1/conf/preprocess.yaml b/examples/aishell/asr1/conf/preprocess.yaml
index 6fccd1954..d3992cb9f 100644
--- a/examples/aishell/asr1/conf/preprocess.yaml
+++ b/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
diff --git a/examples/aishell/asr1/conf/tuning/decode.yaml b/examples/aishell/asr1/conf/tuning/decode.yaml
index f0a5ba6b5..72ede9272 100644
--- a/examples/aishell/asr1/conf/tuning/decode.yaml
+++ b/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.
diff --git a/examples/aishell/asr1/run.sh b/examples/aishell/asr1/run.sh
index be7116a75..c54dae9cf 100644
--- a/examples/aishell/asr1/run.sh
+++ b/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!!!
diff --git a/paddlespeech/__init__.py b/paddlespeech/__init__.py
index 92c1df7c4..b781c4a8e 100644
--- a/paddlespeech/__init__.py
+++ b/paddlespeech/__init__.py
@@ -14,6 +14,3 @@
import _locale
_locale._getdefaultlocale = (lambda *args: ['en_US', 'utf8'])
-
-
-
diff --git a/paddlespeech/s2t/exps/u2/bin/test_wav.py b/paddlespeech/s2t/exps/u2/bin/test_wav.py
index 6bc86d8f8..86c3db89f 100644
--- a/paddlespeech/s2t/exps/u2/bin/test_wav.py
+++ b/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
diff --git a/paddlespeech/server/conf/ws_application.yaml b/paddlespeech/server/conf/ws_application.yaml
index b2eaf5001..b958bdf69 100644
--- a/paddlespeech/server/conf/ws_application.yaml
+++ b/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']
diff --git a/paddlespeech/server/tests/asr/online/websocket_client.py b/paddlespeech/server/tests/asr/online/websocket_client.py
index 58506606e..661eb4dd9 100644
--- a/paddlespeech/server/tests/asr/online/websocket_client.py
+++ b/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
diff --git a/paddlespeech/server/ws/asr_socket.py b/paddlespeech/server/ws/asr_socket.py
index 65c04f67f..ad4a1124e 100644
--- a/paddlespeech/server/ws/asr_socket.py
+++ b/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()
diff --git a/paddlespeech/vector/cluster/diarization.py b/paddlespeech/vector/cluster/diarization.py
index 5b2157257..816ab0dee 100644
--- a/paddlespeech/vector/cluster/diarization.py
+++ b/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
diff --git a/setup.py b/setup.py
index 9a8bb66bb..82ff63412 100644
--- a/setup.py
+++ b/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):
diff --git a/utils/DER.py b/utils/DER.py
index 59bcbec47..d6ab695d8 100755
--- a/utils/DER.py
+++ b/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.]+")