speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update docs

Browse Source
This commit is contained in:
雾聪 2023-11-13 17:43:08 +08:00
parent e9799f5f1f
commit 923689bb07
9 changed files with 77 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
runtime/docs/SDK_advanced_guide_offline.md
View File

@ -83,13 +83,13 @@ nohup bash run_server.sh \
Introduction to run_server.sh parameters:
```text
--download-model-dir: Model download address, download models from Modelscope by setting the model ID.
--model-dir: Modelscope model ID.
--model-dir: modelscope model ID or local model path.
--quantize: True for quantized ASR model, False for non-quantized ASR model. Default is True.
--vad-dir: Modelscope model ID.
--vad-dir: modelscope model ID or local model path.
--vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True.
--punc-dir: Modelscope model ID.
--punc-dir: modelscope model ID or local model path.
--punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True.
--itn-dir modelscope model ID
--itn-dir modelscope model ID or local model path.
--port: Port number that the server listens on. Default is 10095.
--decoder-thread-num: Number of inference threads that the server starts. Default is 8.
--io-thread-num: Number of IO threads that the server starts. Default is 1.

8
runtime/docs/SDK_advanced_guide_offline_en.md
View File

@ -65,13 +65,13 @@ nohup bash run_server.sh \
Introduction to run_server.sh parameters:
```text
--download-model-dir: Model download address, download models from Modelscope by setting the model ID.
--model-dir: Modelscope model ID.
--model-dir: modelscope model ID or local model path.
--quantize: True for quantized ASR model, False for non-quantized ASR model. Default is True.
--vad-dir: Modelscope model ID.
--vad-dir: modelscope model ID or local model path.
--vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True.
--punc-dir: Modelscope model ID.
--punc-dir: modelscope model ID or local model path.
--punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True.
--itn-dir modelscope model ID
--itn-dir modelscope model ID or local model path.
--port: Port number that the server listens on. Default is 10095.
--decoder-thread-num: Number of inference threads that the server starts. Default is 8.
--io-thread-num: Number of IO threads that the server starts. Default is 1.

8
runtime/docs/SDK_advanced_guide_offline_en_zh.md
View File

@ -150,13 +150,13 @@ nohup bash run_server.sh \
**run_server.sh命令参数介绍**
```text
--download-model-dir 模型下载地址，通过设置model ID从Modelscope下载模型
--model-dir modelscope model ID
--model-dir modelscope model ID 或者 本地模型路径
--quantize True为量化ASR模型，False为非量化ASR模型，默认是True
--vad-dir modelscope model ID
--vad-dir modelscope model ID 或者 本地模型路径
--vad-quant True为量化VAD模型，False为非量化VAD模型，默认是True
--punc-dir modelscope model ID
--punc-dir modelscope model ID 或者 本地模型路径
--punc-quant True为量化PUNC模型，False为非量化PUNC模型，默认是True
--itn-dir modelscope model ID
--itn-dir modelscope model ID 或者 本地模型路径
--port 服务端监听的端口号，默认为 10095
--decoder-thread-num 服务端启动的推理线程数，默认为 8
--io-thread-num 服务端启动的IO线程数，默认为 1

10
runtime/docs/SDK_advanced_guide_offline_zh.md
View File

@ -164,14 +164,14 @@ nohup bash run_server.sh \
**run_server.sh命令参数介绍**
```text
--download-model-dir 模型下载地址，通过设置model ID从Modelscope下载模型
--model-dir modelscope model ID
--model-dir modelscope model ID 或者 本地模型路径
--quantize True为量化ASR模型，False为非量化ASR模型，默认是True
--vad-dir modelscope model ID
--vad-dir modelscope model ID 或者 本地模型路径
--vad-quant True为量化VAD模型，False为非量化VAD模型，默认是True
--punc-dir modelscope model ID
--punc-dir modelscope model ID 或者 本地模型路径
--punc-quant True为量化PUNC模型，False为非量化PUNC模型，默认是True
--lm-dir modelscope model ID
--itn-dir modelscope model ID
--lm-dir modelscope model ID 或者 本地模型路径
--itn-dir modelscope model ID 或者 本地模型路径
--port 服务端监听的端口号，默认为 10095
--decoder-thread-num 服务端启动的推理线程数，默认为 8
--io-thread-num 服务端启动的IO线程数，默认为 1

8
runtime/docs/SDK_advanced_guide_online.md
View File

@ -100,14 +100,14 @@ nohup bash run_server_2pass.sh \
### More details about the script run_server_2pass.sh:
```text
--download-model-dir: Model download address, download models from Modelscope by setting the model ID.
--model-dir: Modelscope model ID.
--model-dir: modelscope model ID or local model path.
--online-model-dir modelscope model ID
--quantize: True for quantized ASR model, False for non-quantized ASR model. Default is True.
--vad-dir: Modelscope model ID.
--vad-dir: modelscope model ID or local model path.
--vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True.
--punc-dir: Modelscope model ID.
--punc-dir: modelscope model ID or local model path.
--punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True.
--itn-dir modelscope model ID
--itn-dir modelscope model ID or local model path.
--port: Port number that the server listens on. Default is 10095.
--decoder-thread-num: Number of inference threads that the server starts. Default is 8.
--io-thread-num: Number of IO threads that the server starts. Default is 1.

10
runtime/docs/SDK_advanced_guide_online_zh.md
View File

@ -108,14 +108,14 @@ nohup bash run_server_2pass.sh \
**run_server_2pass.sh命令参数介绍**
```text
--download-model-dir 模型下载地址，通过设置model ID从Modelscope下载模型
--model-dir modelscope model ID
--online-model-dir modelscope model ID
--model-dir modelscope model ID 或者 本地模型路径
--online-model-dir modelscope model ID 或者 本地模型路径
--quantize True为量化ASR模型，False为非量化ASR模型，默认是True
--vad-dir modelscope model ID
--vad-dir modelscope model ID 或者 本地模型路径
--vad-quant True为量化VAD模型，False为非量化VAD模型，默认是True
--punc-dir modelscope model ID
--punc-dir modelscope model ID 或者 本地模型路径
--punc-quant True为量化PUNC模型，False为非量化PUNC模型，默认是True
--itn-dir modelscope model ID
--itn-dir modelscope model ID 或者 本地模型路径
--port 服务端监听的端口号，默认为 10095
--decoder-thread-num 服务端启动的推理线程数，默认为 8
--io-thread-num 服务端启动的IO线程数，默认为 1

4
runtime/onnxruntime/readme.md
View File

@ -36,12 +36,12 @@ make -j 4
## Building for Windows
### Download onnxruntime
https://github.com/BtbN/FFmpeg-Builds/releases/download/latest/ffmpeg-master-latest-win64-gpl-shared.zip
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-win-x64-1.16.1.zip
Download and unzip to d:\ffmpeg-master-latest-win64-gpl-shared
### Download ffmpeg
https://github.com/microsoft/onnxruntime/releases/download/v1.16.1/onnxruntime-win-x64-1.16.1.zip
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-win64-gpl-shared.zip
Download and unzip to d:\onnxruntime-win-x64-1.16.1

46
runtime/websocket/readme.md
View File

@ -6,14 +6,14 @@
## Building for Linux/Unix
### Download onnxruntime
```shell
wget https://github.com/microsoft/onnxruntime/releases/download/v1.14.0/onnxruntime-linux-x64-1.14.0.tgz
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-linux-x64-1.14.0.tgz
tar -zxvf onnxruntime-linux-x64-1.14.0.tgz
```
### Download ffmpeg
```shell
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
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-linux64-gpl-shared.tar.xz
tar -xvf ffmpeg-master-latest-linux64-gpl-shared.tar.xz
```
### Install deps
@ -31,6 +31,44 @@ apt-get install libssl-dev #ubuntu
```shell
git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR/runtime/websocket
mkdir build && cd build
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
cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0 -DFFMPEG_DIR=/path/to/ffmpeg-master-latest-linux64-gpl-shared
make -j 4
```
## Building for Windows
### Download onnxruntime
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-win-x64-1.16.1.zip
Download to d:\ffmpeg-master-latest-win64-gpl-shared
### Download ffmpeg
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-win64-gpl-shared.zip
Download to d:\onnxruntime-win-x64-1.16.1
### Download openssl
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/openssl-1.1.1w.tar.gz
Download to d:/src/openssl-1.1.1w
Open x64 Native Tools Command Prompt and execute the following compilation steps
```
d:
cd d:/src/openssl-1.1.1w
perl Configure VC-WIN64A --prefix=d:/openssl-1.1.1w
nmake
namke install
```
### Build runtime
```
git clone https://github.com/alibaba-damo-academy/FunASR.git
cd FunASR/runtime/websocket
mkdir build
cd build
cmake ../ -D OPENSSL_ROOT_DIR=d:/openssl-1.1.1w -D FFMPEG_DIR=d:/ffmpeg-master-latest-win64-gpl-shared -D ONNXRUNTIME_DIR=d:/onnxruntime-win-x64-1.16.1
```
Open FunASRWebscoket.sln in Visual Studio and complete the compilation.

14
runtime/websocket/readme_zh.md
View File

@ -6,14 +6,14 @@
## Linux/Unix 平台编译
### 下载 onnxruntime
```shell
wget https://github.com/microsoft/onnxruntime/releases/download/v1.14.0/onnxruntime-linux-x64-1.14.0.tgz
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-linux-x64-1.14.0.tgz
tar -zxvf onnxruntime-linux-x64-1.14.0.tgz
```
### 下载 ffmpeg
```shell
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
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-linux64-gpl-shared.tar.xz
tar -xvf ffmpeg-master-latest-linux64-gpl-shared.tar.xz
```
### 安装依赖
@ -32,24 +32,24 @@ apt-get install libssl-dev #ubuntu
```shell
git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR/runtime/websocket
mkdir build && cd build
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
cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0 -DFFMPEG_DIR=/path/to/ffmpeg-master-latest-linux64-gpl-shared
make -j 4
```
## Windows 平台编译
### 下载 onnxruntime
https://github.com/BtbN/FFmpeg-Builds/releases/download/latest/ffmpeg-master-latest-win64-gpl-\shared.zip
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/onnxruntime-win-x64-1.16.1.zip
下载并解压到 d:\ffmpeg-master-latest-win64-gpl-shared
### 下载 ffmpeg
https://github.com/microsoft/onnxruntime/releases/download/v1.16.1/onnxruntime-win-x64-1.16.1.zip
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-master-latest-win64-gpl-shared.zip
下载并解压到 d:\onnxruntime-win-x64-1.16.1
### 编译 openssl
https://www.openssl.org/source/openssl-1.1.1w.tar.gz
https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/openssl-1.1.1w.tar.gz
下载解压到 d:/src/openssl-1.1.1w