v0.6.8

游雁

2023-07-03 fbe73e18846a81bc0800f8cbbe72644d0394a530

v0.6.8

 funasr/runtime/python/websocket/README.md

@@ -36,7 +36,7 @@
```
##### 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 @@
--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 @@
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

 funasr/runtime/python/websocket/parse_args.py

File was deleted

 funasr/runtime/python/websocket/wss_client_asr.py

@@ -42,10 +42,10 @@
                    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 @@
                    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

 funasr/runtime/python/websocket/wss_srv_asr.py

@@ -5,8 +5,8 @@
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 @@
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()