From c2e4e3c2e9be855277d9f4fa9cd0544892ff829a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 30 八月 2023 09:57:30 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

---
 funasr/runtime/python/websocket/README.md |  103 ++++++++++++++++++++++++++++++++++-----------------
 1 files changed, 68 insertions(+), 35 deletions(-)

diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index 76405ea..686ad86 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -1,6 +1,6 @@
 # Service with websocket-python
 
-This is a demo using funasr pipeline with websocket python-api. 
+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
 
@@ -21,23 +21,23 @@
 ```
 
 ### Start server
-#### ASR offline server
+
+##### API-reference
 ```shell
-python ws_server_offline.py --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+python funasr_wss_server.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] 
 ```
-
-#### ASR streaming server
+##### Usage examples
 ```shell
-python ws_server_online.py --port 10095 --asr_model_online "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
+python funasr_wss_server.py --port 10095
 ```
-
-#### 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
 
@@ -47,33 +47,66 @@
 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
-#### ASR offline client
-##### Recording from mircrophone
+#### API-reference
 ```shell
-# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
-python ws_client.py --host "0.0.0.0" --port 10095 --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 ws_client.py --host "0.0.0.0" --port 10095 --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --send_without_sleep
-```
-#### ASR streaming client
-##### Recording from mircrophone
-```shell
-# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python ws_client.py --host "0.0.0.0" --port 10095 --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 ws_client.py --host "0.0.0.0" --port 10095 --chunk_size "5,10,5" --audio_in "./data/wav.scp" --words_max_print 100
+python funasr_wss_client.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] \
+--mode [`online` for streaming asr, `offline` for non-streaming, `2pass` for unifying streaming and non-streaming asr] \
+--thread_num [thread_num for send data]
 ```
 
-#### ASR offline/online 2pass client
+#### Usage examples
+##### ASR offline client
+Recording from mircrophone
+```shell
+# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
+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 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 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 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 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 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).
 2. We acknowledge [zhaoming](https://github.com/zhaomingwork/FunASR/tree/fix_bug_for_python_websocket) for contributing the websocket service.

--
Gitblit v1.9.1