From 1988fe85f6d4e2d2f809e705e13d69d0b57bd0fc Mon Sep 17 00:00:00 2001 From: shixian.shi <shixian.shi@alibaba-inc.com> Date: 星期四, 04 五月 2023 19:27:00 +0800 Subject: [PATCH] update --- funasr/runtime/python/websocket/README.md | 49 +++++++++++++++++++++++++++++++++++-------------- 1 files changed, 35 insertions(+), 14 deletions(-) diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md index 2c0dec1..ee7dca0 100644 --- a/funasr/runtime/python/websocket/README.md +++ b/funasr/runtime/python/websocket/README.md @@ -1,31 +1,45 @@ -# Using funasr with websocket -We can send streaming audio data to server in real-time with grpc client every 300 ms e.g., and get transcribed text when stop speaking. -The audio data is in streaming, the asr inference process is in offline. +# Service with websocket-python -# Steps +This is a demo using funasr pipeline with websocket python-api. ## For the Server -Install the modelscope and funasr +### Install the modelscope and funasr ```shell -pip install "modelscope[audio_asr]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html +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 -pip install --editable ./ ``` -Install the requirements for server +### Install the requirements for server ```shell cd funasr/runtime/python/websocket pip install -r requirements_server.txt ``` -Start server +### Start server +#### ASR offline server +[//]: # (```shell) + +[//]: # (python ws_server_online.py --host "0.0.0.0" --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch") + +[//]: # (```) +#### ASR streaming server ```shell -python ASR_server.py --host "0.0.0.0" --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" +python ws_server_online.py --host "0.0.0.0" --port 10095 --asr_model_online "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online" ``` + +#### ASR offline/online 2pass server + +[//]: # (```shell) + +[//]: # (python ws_server_online.py --host "0.0.0.0" --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch") + +[//]: # (```) ## For the client @@ -36,11 +50,18 @@ pip install -r requirements_client.txt ``` -Start client - +### Start client +#### Recording from mircrophone ```shell -python ASR_client.py --host "127.0.0.1" --port 10095 --chunk_size 300 +# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms +python ws_client.py --host "127.0.0.1" --port 10095 --chunk_size "5,10,5" +``` +#### Loadding from wav.scp(kaldi style) +```shell +# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms +python ws_client.py --host "127.0.0.1" --port 10095 --chunk_size "5,10,5" --audio_in "./data/wav.scp" ``` ## Acknowledge -1. We acknowledge [cgisky1980](https://github.com/cgisky1980/FunASR) for contributing the websocket service. +1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR). +2. We acknowledge [cgisky1980](https://github.com/cgisky1980/FunASR) for contributing the websocket service. -- Gitblit v1.9.1