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 | 19 +++++++++++-------- 1 files changed, 11 insertions(+), 8 deletions(-) diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md index 723782f..ee7dca0 100644 --- a/funasr/runtime/python/websocket/README.md +++ b/funasr/runtime/python/websocket/README.md @@ -1,7 +1,6 @@ -# 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 +This is a demo using funasr pipeline with websocket python-api. ## For the Server @@ -31,9 +30,8 @@ [//]: # (```) #### ASR streaming server ```shell -python ws_server_online.py --host "0.0.0.0" --port 10095 +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 @@ -52,11 +50,16 @@ pip install -r requirements_client.txt ``` -Start client - +### Start client +#### Recording from mircrophone ```shell # --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms -python ws_client.py --host "127.0.0.1" --port 10096 --chunk_size "5,10,5" +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 -- Gitblit v1.9.1