From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn

---
 funasr/runtime/python/websocket/README.md |   88 +++++++++++++++++++++++++++++++++++++-------
 1 files changed, 74 insertions(+), 14 deletions(-)

diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index 2c0dec1..fcdc83c 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -1,30 +1,42 @@
-# 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. It supports the offline, online, offline/online-2pass unifying speech recognition. 
 
 ## 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
 
+##### API-reference
 ```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 wss_srv_asr.py \
+--port [port id] \
+--asr_model [asr model_name] \
+--asr_model_online [asr model_name] \
+--punc_model [punc model_name] \
+--ngpu [0 or 1] \
+--ncpu [1 or 4] \
+--certfile [path of certfile for ssl] \
+--keyfile [path of keyfile for ssl] 
+```
+##### 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"
 ```
 
 ## For the client
@@ -36,11 +48,59 @@
 pip install -r requirements_client.txt
 ```
 
-Start client
-
+### Start client
+#### API-reference
 ```shell
-python ASR_client.py --host "127.0.0.1" --port 10095 --chunk_size 300
+python wss_client_asr.py \
+--host [ip_address] \
+--port [port id] \
+--chunk_size ["5,10,5"=600ms, "8,8,4"=480ms] \
+--chunk_interval [duration of send chunk_size/chunk_interval] \
+--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] \
 ```
 
+#### Usage examples
+##### ASR offline client
+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
+```
+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" --send_without_sleep --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
+```
+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"
+```
+
+##### 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"
+```
+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"
+```
 ## 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 [zhaoming](https://github.com/zhaomingwork/FunASR/tree/fix_bug_for_python_websocket) for contributing the websocket service.
+3. We acknowledge [cgisky1980](https://github.com/cgisky1980/FunASR) for contributing the websocket service of offline model.

--
Gitblit v1.9.1