speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

v0.6.8

Browse Source
This commit is contained in:
游雁 2023-07-03 17:37:15 +08:00
parent 0a057b1013
commit fbe73e1884
4 changed files with 60 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
funasr/runtime/python/websocket/README.md
View File

@ -36,7 +36,7 @@ python wss_srv_asr.py \
```
##### Usage examples
```shell
python wss_srv_asr.py --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" --asr_model_online "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
python wss_srv_asr.py --port 10095
```
## For the client
@ -59,9 +59,8 @@ python wss_client_asr.py \
--words_max_print [max number of words to print] \
--audio_in [if set, loadding from wav.scp, else recording from mircrophone] \
--output_dir [if set, write the results to output_dir] \
--send_without_sleep [only set for offline] \
--ssl [1 for wss connect, 0 for ws, default is 1] \
--mode [`online` for streaming asr, `offline` for non-streaming, `2pass` for unifying streaming and non-streaming asr] \
--thread_num [thread_num for send data]
```
#### Usage examples
@ -69,19 +68,19 @@ python wss_client_asr.py \
Recording from mircrophone
```shell
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline
```
Loadding from wav.scp(kaldi style)
```shell
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --output_dir "./results"
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --audio_in "./data/wav.scp" --output_dir "./results"
```
##### ASR streaming client
Recording from mircrophone
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" --words_max_print 100
python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5"
```
Loadding from wav.scp(kaldi style)
```shell

50
funasr/runtime/python/websocket/parse_args.py
View File

@ -1,50 +0,0 @@
# -*- encoding: utf-8 -*-
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--host",
type=str,
default="0.0.0.0",
required=False,
help="host ip, localhost, 0.0.0.0")
parser.add_argument("--port",
type=int,
default=10095,
required=False,
help="grpc server port")
parser.add_argument("--asr_model",
type=str,
default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
help="model from modelscope")
parser.add_argument("--asr_model_online",
type=str,
default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
help="model from modelscope")
parser.add_argument("--vad_model",
type=str,
default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
help="model from modelscope")
parser.add_argument("--punc_model",
type=str,
default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
help="model from modelscope")
parser.add_argument("--ngpu",
type=int,
default=1,
help="0 for cpu, 1 for gpu")
parser.add_argument("--ncpu",
type=int,
default=4,
help="cpu cores")
parser.add_argument("--certfile",
type=str,
default="./ssl_key/server.crt",
required=False,
help="certfile for ssl")
parser.add_argument("--keyfile",
type=str,
default="./ssl_key/server.key",
required=False,
help="keyfile for ssl")
args = parser.parse_args()
print(args)

12
funasr/runtime/python/websocket/wss_client_asr.py
View File

@ -42,10 +42,10 @@ parser.add_argument("--send_without_sleep",
action="store_true",
default=True,
help="if audio_in is set, send_without_sleep")
parser.add_argument("--test_thread_num",
parser.add_argument("--thread_num",
type=int,
default=1,
help="test_thread_num")
help="thread_num")
parser.add_argument("--words_max_print",
type=int,
default=10000,
@ -311,16 +311,16 @@ if __name__ == '__main__':
f'Not supported audio type: {audio_type}')
total_len = len(wavs)
if total_len >= args.test_thread_num:
chunk_size = int(total_len / args.test_thread_num)
remain_wavs = total_len - chunk_size * args.test_thread_num
if total_len >= args.thread_num:
chunk_size = int(total_len / args.thread_num)
remain_wavs = total_len - chunk_size * args.thread_num
else:
chunk_size = 1
remain_wavs = 0
process_list = []
chunk_begin = 0
for i in range(args.test_thread_num):
for i in range(args.thread_num):
now_chunk_size = chunk_size
if remain_wavs > 0:
now_chunk_size = chunk_size + 1

50
funasr/runtime/python/websocket/wss_srv_asr.py
View File

@ -5,8 +5,8 @@ import time
import logging
import tracemalloc
import numpy as np
import argparse
import ssl
from parse_args import args
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
@ -17,6 +17,54 @@ tracemalloc.start()
logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)
parser = argparse.ArgumentParser()
parser.add_argument("--host",
type=str,
default="0.0.0.0",
required=False,
help="host ip, localhost, 0.0.0.0")
parser.add_argument("--port",
type=int,
default=10095,
required=False,
help="grpc server port")
parser.add_argument("--asr_model",
type=str,
default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
help="model from modelscope")
parser.add_argument("--asr_model_online",
type=str,
default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
help="model from modelscope")
parser.add_argument("--vad_model",
type=str,
default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
help="model from modelscope")
parser.add_argument("--punc_model",
type=str,
default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
help="model from modelscope")
parser.add_argument("--ngpu",
type=int,
default=1,
help="0 for cpu, 1 for gpu")
parser.add_argument("--ncpu",
type=int,
default=4,
help="cpu cores")
parser.add_argument("--certfile",
type=str,
default="./ssl_key/server.crt",
required=False,
help="certfile for ssl")
parser.add_argument("--keyfile",
type=str,
default="./ssl_key/server.key",
required=False,
help="keyfile for ssl")
args = parser.parse_args()
websocket_users = set()