From 1ce704d8c09bd4d4c7e5ab087f951f31fad9fca6 Mon Sep 17 00:00:00 2001 From: nichongjia-2007 <nichongjia@gmail.com> Date: 星期五, 07 七月 2023 15:47:19 +0800 Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR --- funasr/runtime/python/websocket/README.md | 29 ++++++++++++++++++----------- 1 files changed, 18 insertions(+), 11 deletions(-) diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md index ed44795..686ad86 100644 --- a/funasr/runtime/python/websocket/README.md +++ b/funasr/runtime/python/websocket/README.md @@ -24,7 +24,7 @@ ##### API-reference ```shell -python wss_srv_asr.py \ +python funasr_wss_server.py \ --port [port id] \ --asr_model [asr model_name] \ --asr_model_online [asr model_name] \ @@ -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 funasr_wss_server.py --port 10095 ``` ## For the client @@ -47,11 +47,19 @@ cd funasr/runtime/python/websocket pip install -r requirements_client.txt ``` +If you want infer from videos, you should install `ffmpeg` +```shell +apt-get install -y ffmpeg #ubuntu +# yum install -y ffmpeg # centos +# brew install ffmpeg # mac +# winget install ffmpeg # wins +pip3 install websockets ffmpeg-python +``` ### Start client #### API-reference ```shell -python wss_client_asr.py \ +python funasr_wss_client.py \ --host [ip_address] \ --port [port id] \ --chunk_size ["5,10,5"=600ms, "8,8,4"=480ms] \ @@ -59,9 +67,8 @@ --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 @@ -69,36 +76,36 @@ 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 funasr_wss_client.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 funasr_wss_client.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 funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" ``` Loadding from wav.scp(kaldi style) ```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" --audio_in "./data/wav.scp" --output_dir "./results" +python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode online --chunk_size "5,10,5" --audio_in "./data/wav.scp" --output_dir "./results" ``` ##### ASR offline/online 2pass 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 2pass --chunk_size "8,8,4" +python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" ``` Loadding from wav.scp(kaldi style) ```shell # --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms -python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results" +python funasr_wss_client.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results" ``` ## Acknowledge 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR). -- Gitblit v1.9.1