This is a demo using funasr pipeline with websocket python-api.
pip install -U modelscope funasr
# For the users in China, you could install with the command:
# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
git clone https://github.com/alibaba/FunASR.git && cd FunASR
cd funasr/runtime/python/websocket
pip install -r requirements_server.txt
python ws_server_offline.py --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
python ws_server_online.py --port 10095 --asr_model_online "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
Install the requirements for clientshell git clone https://github.com/alibaba/FunASR.git && cd FunASR cd funasr/runtime/python/websocket pip install -r requirements_client.txt
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
python ws_client.py --host "0.0.0.0" --port 10095 --chunk_interval 10 --words_max_print 100
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
python ws_client.py --host "0.0.0.0" --port 10095 --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
python ws_client.py --host "0.0.0.0" --port 10095 --chunk_size "5,10,5" --words_max_print 100
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
python ws_client.py --host "0.0.0.0" --port 10095 --chunk_size "5,10,5" --audio_in "./data/wav.scp" --words_max_print 100 --output_dir "./results"