From c542eacb0aadcbc49c63db40429fca4e08f807a4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 七月 2023 10:27:35 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/runtime/websocket/readme.md | 156 +++++++++++++++++++++++++++++++++++++---------------
1 files changed, 111 insertions(+), 45 deletions(-)
diff --git a/funasr/runtime/websocket/readme.md b/funasr/runtime/websocket/readme.md
index 4b2d55a..414d6b8 100644
--- a/funasr/runtime/websocket/readme.md
+++ b/funasr/runtime/websocket/readme.md
@@ -1,19 +1,27 @@
-# ONNXRuntime-cpp for Websocket Server
+([绠�浣撲腑鏂嘳(https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/websocket/readme_zh.md)|English)
+
+# Service with websocket-cpp
## Export the model
### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
```shell
# pip3 install torch torchaudio
-pip install -U modelscope funasr
+pip3 install -U modelscope funasr
# For the users in China, you could install with the command:
-# pip install -U modelscope funasr -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
+# pip3 install -U modelscope funasr -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
```
### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)
```shell
-python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
+python -m funasr.export.export_model \
+--export-dir ./export \
+--type onnx \
+--quantize True \
+--model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
+--model-name damo/speech_fsmn_vad_zh-cn-16k-common-pytorch \
+--model-name damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch
```
## Building for Linux/Unix
@@ -26,6 +34,15 @@
tar -zxvf onnxruntime-linux-x64-1.14.0.tgz
```
+### Download ffmpeg
+```shell
+wget https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2023-07-09-12-50/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+tar -xvf ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+# 鍥藉唴鍙互浣跨敤涓嬭堪鏂瑰紡
+# wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+# tar -xvf ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+```
+
### Install openblas
```shell
sudo apt-get install libopenblas-dev #ubuntu
@@ -33,64 +50,113 @@
```
### Build runtime
+required openssl lib
+
```shell
-git clone https://github.com/alibaba-damo-academy/FunASR.git && cd funasr/runtime/websocket
+apt-get install libssl-dev #ubuntu
+# yum install openssl-devel #centos
+
+
+git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR/funasr/runtime/websocket
mkdir build && cd build
-cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0
+cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0 -DFFMPEG_DIR=/path/to/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared
make
```
## Run the websocket server
```shell
cd bin
-websocketmain [--model_thread_num <int>] [--decoder_thread_num
- <int>] [--io_thread_num <int>] [--port <int>]
- [--listen_ip <string>] [--wav-scp <string>]
- [--wav-path <string>] [--punc-config <string>]
- [--punc-model <string>] --am-config <string>
- --am-cmvn <string> --am-model <string>
- [--vad-config <string>] [--vad-cmvn <string>]
- [--vad-model <string>] [--] [--version] [-h]
+./funasr-wss-server [--download-model-dir <string>]
+ [--model-thread-num <int>] [--decoder-thread-num <int>]
+ [--io-thread-num <int>] [--port <int>] [--listen_ip
+ <string>] [--punc-quant <string>] [--punc-dir <string>]
+ [--vad-quant <string>] [--vad-dir <string>] [--quantize
+ <string>] --model-dir <string> [--keyfile <string>]
+ [--certfile <string>] [--] [--version] [-h]
Where:
- --wav-scp <string>
- wave scp path
- --wav-path <string>
- wave file path
+ --download-model-dir <string>
+ Download model from Modelscope to download_model_dir
- --punc-config <string>
- punc config path
- --punc-model <string>
- punc model path
+ --model-dir <string>
+ default: /workspace/models/asr, the asr model path, which contains model_quant.onnx, config.yaml, am.mvn
+ --quantize <string>
+ true (Default), load the model of model_quant.onnx in model_dir. If set false, load the model of model.onnx in model_dir
- --am-config <string>
- (required) am config path
- --am-cmvn <string>
- (required) am cmvn path
- --am-model <string>
- (required) am model path
+ --vad-dir <string>
+ default: /workspace/models/vad, the vad model path, which contains model_quant.onnx, vad.yaml, vad.mvn
+ --vad-quant <string>
+ true (Default), load the model of model_quant.onnx in vad_dir. If set false, load the model of model.onnx in vad_dir
- --vad-config <string>
- vad config path
- --vad-cmvn <string>
- vad cmvn path
- --vad-model <string>
- vad model path
- --decoder_thread_num <int>
- number of threads for decoder
- --io_thread_num <int>
- number of threads for network io
+ --punc-dir <string>
+ default: /workspace/models/punc, the punc model path, which contains model_quant.onnx, punc.yaml
+ --punc-quant <string>
+ true (Default), load the model of model_quant.onnx in punc_dir. If set false, load the model of model.onnx in punc_dir
+
+ --decoder-thread-num <int>
+ number of threads for decoder, default:8
+ --io-thread-num <int>
+ number of threads for network io, default:8
+ --port <int>
+ listen port, default:10095
+ --certfile <string>
+ default: ../../../ssl_key/server.crt, path of certficate for WSS connection. if it is empty, it will be in WS mode.
+ --keyfile <string>
+ default: ../../../ssl_key/server.key, path of keyfile for WSS connection
- Required: --am-config <string> --am-cmvn <string> --am-model <string>
- If use vad, please add: [--vad-config <string>] [--vad-cmvn <string>] [--vad-model <string>]
- If use punc, please add: [--punc-config <string>] [--punc-model <string>]
example:
-./bin/websocketmain --am-config /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/config.yaml --am-model /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.onnx --am-cmvn /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/am.mvn
+# you can use models downloaded from modelscope or local models:
+# download models from modelscope
+./funasr-wss-server \
+ --download-model-dir /workspace/models \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+
+# load models from local paths
+./funasr-wss-server \
+ --model-dir /workspace/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --vad-dir /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --punc-dir /workspace/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+
```
## Run websocket client test
-Usage: websocketclient server_ip port wav_path threads_num
+
+```shell
+./funasr-wss-client --server-ip <string>
+ --port <string>
+ --wav-path <string>
+ [--thread-num <int>]
+ [--is-ssl <int>] [--]
+ [--version] [-h]
+
+Where:
+ --server-ip <string>
+ (required) server-ip
+
+ --port <string>
+ (required) port
+
+ --wav-path <string>
+ (required) the input could be: wav_path, e.g.: asr_example.wav;
+ pcm_path, e.g.: asr_example.pcm; wav.scp, kaldi style wav list (wav_id \t wav_path)
+
+ --thread-num <int>
+ thread-num
+
+ --is-ssl <int>
+ is-ssl is 1 means use wss connection, or use ws connection
+
example:
-websocketclient 127.0.0.1 8889 funasr/runtime/websocket/test.pcm.wav 64
+./funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path test.wav --thread-num 1 --is-ssl 1
+
result json, example like:
-{"text":"涓�浜屼笁鍥涗簲鍏竷鍏節鍗佷竴浜屼笁鍥涗簲鍏竷鍏節鍗�"}
+{"mode":"offline","text":"娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�","wav_name":"wav2"}
+```
+
+
+## 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/add-offline-websocket-srv/funasr/runtime/websocket) for contributing the websocket(cpp-api).
+
--
Gitblit v1.9.1