From 4137f5cf26e7c4b40853959cd2574edfde03aa60 Mon Sep 17 00:00:00 2001 From: 志浩 <neo.dzh@alibaba-inc.com> Date: 星期五, 07 四月 2023 21:03:34 +0800 Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR into dev_dzh --- funasr/runtime/python/websocket/README.md | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 45 insertions(+), 0 deletions(-) diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md new file mode 100644 index 0000000..353cfa6 --- /dev/null +++ b/funasr/runtime/python/websocket/README.md @@ -0,0 +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. + + +## For the Server + +Install the modelscope and funasr + +```shell +pip install "modelscope[audio_asr]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html +git clone https://github.com/alibaba/FunASR.git && cd FunASR +pip install --editable ./ +``` + +Install the requirements for server + +```shell +cd funasr/runtime/python/websocket +pip install -r requirements_server.txt +``` + +Start 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" +``` + +## For the client + +Install the requirements for client +```shell +git clone https://github.com/alibaba/FunASR.git && cd FunASR +cd funasr/runtime/python/websocket +pip install -r requirements_client.txt +``` + +Start client + +```shell +python ASR_client.py --host "127.0.0.1" --port 10095 --chunk_size 300 +``` + +## Acknowledge +1. We acknowledge [cgisky1980](https://github.com/cgisky1980/FunASR) for contributing the websocket service. -- Gitblit v1.9.1