first commit for takway.ai
This commit is contained in:
IrvingGao committed
commit
d7a6de771c
3256 files changed
+795173
No files matched your search
@@ -0,0 +1,21 @@
|
||||
# Minimal makefile for Sphinx documentation
|
||||
#
|
||||
|
||||
# You can set these variables from the command line, and also
|
||||
# from the environment for the first two.
|
||||
SPHINXOPTS =
|
||||
SPHINXBUILD = sphinx-build
|
||||
SPHINXPROJ = FunASR
|
||||
SOURCEDIR = .
|
||||
BUILDDIR = _build
|
||||
|
||||
# Put it first so that "make" without argument is like "make help".
|
||||
help:
|
||||
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
|
||||
.PHONY: help Makefile
|
||||
|
||||
# Catch-all target: route all unknown targets to Sphinx using the new
|
||||
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
|
||||
%: Makefile
|
||||
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
@@ -0,0 +1,19 @@
|
||||
# FunASR document generation
|
||||
|
||||
## Generate HTML
|
||||
For convenience, we provide users with the ability to generate local HTML manually.
|
||||
|
||||
First, you should install the following packages, which is required for building HTML:
|
||||
|
||||
```sh
|
||||
pip3 install -U "funasr[docs]"
|
||||
```
|
||||
|
||||
Then you can generate HTML manually.
|
||||
|
||||
```sh
|
||||
cd docs
|
||||
make html
|
||||
```
|
||||
|
||||
The generated files are all contained in the "FunASR/docs/_build" directory. You can access the FunASR documentation by simply opening the "html/index.html" file in your browser from this directory.
|
||||
@@ -0,0 +1,67 @@
|
||||
# Configuration file for the Sphinx documentation builder.
|
||||
#
|
||||
# This file only contains a selection of the most common options. For a full
|
||||
# list see the documentation:
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html
|
||||
|
||||
# -- Path setup --------------------------------------------------------------
|
||||
|
||||
# If extensions (or modules to document with autodoc) are in another directory,
|
||||
# add these directories to sys.path here. If the directory is relative to the
|
||||
# documentation root, use os.path.abspath to make it absolute, like shown here.
|
||||
#
|
||||
# import os
|
||||
# import sys
|
||||
# sys.path.insert(0, os.path.abspath('.'))
|
||||
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
|
||||
project = "FunASR"
|
||||
copyright = "2022, Speech Lab, Alibaba Group"
|
||||
author = "Speech Lab, Alibaba Group"
|
||||
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
|
||||
# Add any Sphinx extension module names here, as strings. They can be
|
||||
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
|
||||
# ones.
|
||||
extensions = [
|
||||
"nbsphinx",
|
||||
"sphinx.ext.autodoc",
|
||||
"sphinx.ext.napoleon",
|
||||
"sphinx.ext.viewcode",
|
||||
"sphinx.ext.mathjax",
|
||||
"sphinx.ext.todo",
|
||||
# "sphinxarg.ext",
|
||||
"sphinx_markdown_tables",
|
||||
"recommonmark",
|
||||
"sphinx_rtd_theme",
|
||||
]
|
||||
|
||||
# Add any paths that contain templates here, relative to this directory.
|
||||
templates_path = ["_templates"]
|
||||
|
||||
source_suffix = [".rst", ".md"]
|
||||
|
||||
# List of patterns, relative to source directory, that match files and
|
||||
# directories to ignore when looking for source files.
|
||||
# This pattern also affects html_static_path and html_extra_path.
|
||||
exclude_patterns = []
|
||||
|
||||
# The name of the Pygments (syntax highlighting) style to use.
|
||||
pygments_style = "sphinx"
|
||||
|
||||
# -- Options for HTML output -------------------------------------------------
|
||||
|
||||
# The theme to use for HTML and HTML Help pages. See the documentation for
|
||||
# a list of builtin themes.
|
||||
#
|
||||
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
# html_static_path = ['_static']
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 21 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 6.9 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 16 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 60 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 24 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 53 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 105 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 624 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 75 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 653 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 41 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 157 KiB |
+121
@@ -0,0 +1,121 @@
|
||||
.. Funasr documentation master file, created by
|
||||
sphinx-quickstart on Tues Dec 6 19:05:00 2022.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
FunASR: A Fundamental End-to-End Speech Recognition Toolkit
|
||||
============================================================
|
||||
.. image:: ./images/funasr_logo.jpg
|
||||
|
||||
FunASR hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model released on `ModelScope <https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition>`_, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun！
|
||||
|
||||
Overview
|
||||
============================================================
|
||||
.. image:: ./images/funasr_overview.png
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Installation
|
||||
|
||||
./installation/installation.md
|
||||
./installation/docker.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 5
|
||||
:caption: Quick Start
|
||||
|
||||
./funasr/quick_start.md
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Academic Egs
|
||||
|
||||
./academic_recipe/asr_recipe.md
|
||||
./academic_recipe/punc_recipe.md
|
||||
./academic_recipe/vad_recipe.md
|
||||
./academic_recipe/sv_recipe.md
|
||||
./academic_recipe/sd_recipe.md
|
||||
|
||||
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: ModelScope Egs
|
||||
|
||||
./modelscope_pipeline/quick_start.md
|
||||
./egs_modelscope/asr/TEMPLATE/README.md
|
||||
./egs_modelscope/vad/TEMPLATE/README.md
|
||||
./egs_modelscope/punctuation/TEMPLATE/README.md
|
||||
./egs_modelscope/tp/TEMPLATE/README.md
|
||||
./modelscope_pipeline/sv_pipeline.md
|
||||
./modelscope_pipeline/sd_pipeline.md
|
||||
./modelscope_pipeline/itn_pipeline.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Huggingface Egs
|
||||
|
||||
Undo
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Model Zoo
|
||||
|
||||
./model_zoo/modelscope_models.md
|
||||
./model_zoo/huggingface_models.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Runtime and Service
|
||||
|
||||
./runtime/readme.md
|
||||
./runtime/docs/SDK_tutorial_online.md
|
||||
./runtime/docs/SDK_tutorial.md
|
||||
./runtime/html5/readme.md
|
||||
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Benchmark and Leaderboard
|
||||
|
||||
./benchmark/benchmark_onnx.md
|
||||
./benchmark/benchmark_onnx_cpp.md
|
||||
./benchmark/benchmark_libtorch.md
|
||||
./benchmark/benchmark_pipeline_cer.md
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Funasr Library
|
||||
|
||||
./reference/build_task.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Papers
|
||||
|
||||
./reference/papers.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Application
|
||||
|
||||
./reference/application.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: FQA
|
||||
|
||||
./reference/FQA.md
|
||||
|
||||
|
||||
Indices and tables
|
||||
==================
|
||||
|
||||
* :ref:`genindex`
|
||||
* :ref:`modindex`
|
||||
* :ref:`search`
|
||||
@@ -0,0 +1,72 @@
|
||||
([简体中文](./docker_zh.md)|English)
|
||||
|
||||
# Docker
|
||||
|
||||
## Install Docker
|
||||
|
||||
### Ubuntu
|
||||
```shell
|
||||
curl -fsSL https://test.docker.com -o test-docker.sh
|
||||
sudo sh test-docker.sh
|
||||
```
|
||||
### Debian
|
||||
```shell
|
||||
curl -fsSL https://get.docker.com -o get-docker.sh
|
||||
sudo sh get-docker.sh
|
||||
```
|
||||
|
||||
### CentOS
|
||||
```shell
|
||||
curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun
|
||||
```
|
||||
|
||||
### MacOS
|
||||
```shell
|
||||
brew install --cask --appdir=/Applications docker
|
||||
```
|
||||
|
||||
### Windows
|
||||
Ref to [docs](https://docs.docker.com/desktop/install/windows-install/)
|
||||
|
||||
## Start Docker
|
||||
```shell
|
||||
sudo systemctl start docker
|
||||
```
|
||||
## Download image
|
||||
|
||||
### Image Hub
|
||||
|
||||
#### CPU
|
||||
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.1`
|
||||
|
||||
#### GPU
|
||||
|
||||
`registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-py38-torch1.11.0-tf1.15.5-1.8.1`
|
||||
|
||||
### Pull Image
|
||||
```shell
|
||||
sudo docker pull <image-name>:<tag>
|
||||
```
|
||||
|
||||
### Check Image
|
||||
```shell
|
||||
sudo docker images
|
||||
```
|
||||
|
||||
## Run Docker
|
||||
```shell
|
||||
# cpu
|
||||
sudo docker run -itd --name funasr -v <local_dir:dir_in_docker> <image-name>:<tag> /bin/bash
|
||||
# gpu
|
||||
sudo docker run -itd --gpus all --name funasr -v <local_dir:dir_in_docker> <image-name>:<tag> /bin/bash
|
||||
|
||||
sudo docker exec -it funasr /bin/bash
|
||||
```
|
||||
|
||||
## Stop Docker
|
||||
```shell
|
||||
exit
|
||||
sudo docker ps
|
||||
sudo docker stop funasr
|
||||
```
|
||||
|
||||
@@ -0,0 +1,72 @@
|
||||
(简体中文|[English](./docker.md))
|
||||
|
||||
# Docker
|
||||
|
||||
## 安装Docker
|
||||
|
||||
### Ubuntu
|
||||
```shell
|
||||
curl -fsSL https://test.docker.com -o test-docker.sh
|
||||
sudo sh test-docker.sh
|
||||
```
|
||||
### Debian
|
||||
```shell
|
||||
curl -fsSL https://get.docker.com -o get-docker.sh
|
||||
sudo sh get-docker.sh
|
||||
```
|
||||
|
||||
### CentOS
|
||||
```shell
|
||||
curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun
|
||||
```
|
||||
|
||||
### MacOS
|
||||
```shell
|
||||
brew install --cask --appdir=/Applications docker
|
||||
```
|
||||
|
||||
### Windows
|
||||
请参考[文档](https://docs.docker.com/desktop/install/windows-install/)
|
||||
|
||||
## 启动Docker
|
||||
```shell
|
||||
sudo systemctl start docker
|
||||
```
|
||||
## 下载Docker镜像
|
||||
|
||||
### 镜像仓库
|
||||
|
||||
#### CPU
|
||||
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.1`
|
||||
|
||||
#### GPU
|
||||
|
||||
`registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-py38-torch1.11.0-tf1.15.5-1.8.1`
|
||||
|
||||
### 拉取镜像
|
||||
```shell
|
||||
sudo docker pull <image-name>:<tag>
|
||||
```
|
||||
|
||||
### 查看镜像
|
||||
```shell
|
||||
sudo docker images
|
||||
```
|
||||
|
||||
## 运行Docker
|
||||
```shell
|
||||
# cpu
|
||||
sudo docker run -itd --name funasr -v <local_dir:dir_in_docker> <image-name>:<tag> /bin/bash
|
||||
# gpu
|
||||
sudo docker run -itd --gpus all --name funasr -v <local_dir:dir_in_docker> <image-name>:<tag> /bin/bash
|
||||
|
||||
sudo docker exec -it funasr /bin/bash
|
||||
```
|
||||
|
||||
## 停止Docker
|
||||
```shell
|
||||
exit
|
||||
sudo docker ps
|
||||
sudo docker stop funasr
|
||||
```
|
||||
|
||||
@@ -0,0 +1,74 @@
|
||||
([简体中文](./installation_zh.md)|English)
|
||||
|
||||
<p align="left">
|
||||
<a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
|
||||
<a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
|
||||
<a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
|
||||
</p>
|
||||
|
||||
## Installation
|
||||
|
||||
### Install Conda (Optional):
|
||||
|
||||
#### Linux
|
||||
```sh
|
||||
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
|
||||
sh Miniconda3-latest-Linux-x86_64.sh
|
||||
source ~/.bashrc
|
||||
conda create -n funasr python=3.8
|
||||
conda activate funasr
|
||||
```
|
||||
#### Mac
|
||||
```sh
|
||||
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
|
||||
# For M1 chip
|
||||
# wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
|
||||
sh Miniconda3-latest-MacOSX*
|
||||
source ~/.zashrc
|
||||
conda create -n funasr python=3.8
|
||||
conda activate funasr
|
||||
```
|
||||
#### Windows
|
||||
Ref to [docs](https://docs.conda.io/en/latest/miniconda.html#windows-installers)
|
||||
|
||||
### Install Pytorch (version >= 1.11.0):
|
||||
|
||||
```sh
|
||||
pip3 install torch torchaudio
|
||||
```
|
||||
If there exists CUDAs in your environments, you should install the pytorch with the version matching the CUDA. The matching list could be found in [docs](https://pytorch.org/get-started/previous-versions/).
|
||||
### Install funasr
|
||||
|
||||
#### Install from pip
|
||||
|
||||
```shell
|
||||
pip3 install -U funasr
|
||||
# For the users in China, you could install with the command:
|
||||
# pip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
#### Or install from source code
|
||||
|
||||
``` sh
|
||||
git clone https://github.com/alibaba/FunASR.git && cd FunASR
|
||||
pip3 install -e ./
|
||||
# For the users in China, you could install with the command:
|
||||
# pip3 install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
### Install modelscope (Optional)
|
||||
If you want to use the pretrained models in ModelScope, you should install the modelscope:
|
||||
|
||||
```shell
|
||||
pip3 install -U modelscope
|
||||
# For the users in China, you could install with the command:
|
||||
# pip3 install -U modelscope -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
### FQA
|
||||
- For installation on MAC M1 chip, the following error may happen:
|
||||
- - _cffi_backend.cpython-38-darwin.so' (mach-o file, but is an incompatible architecture (have (x86_64), need (arm64e)))
|
||||
```shell
|
||||
pip uninstall cffi pycparser
|
||||
ARCHFLAGS="-arch arm64" pip install cffi pycparser --compile --no-cache-dir
|
||||
```
|
||||
@@ -0,0 +1,75 @@
|
||||
(简体中文|[English](./installation.md))
|
||||
|
||||
<p align="left">
|
||||
<a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
|
||||
<a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
|
||||
<a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
|
||||
</p>
|
||||
|
||||
## 安装
|
||||
|
||||
### 安装Conda（可选）：
|
||||
|
||||
#### Linux
|
||||
```sh
|
||||
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
|
||||
sh Miniconda3-latest-Linux-x86_64.sh
|
||||
source ~/.bashrc
|
||||
conda create -n funasr python=3.8
|
||||
conda activate funasr
|
||||
```
|
||||
#### Mac
|
||||
```sh
|
||||
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
|
||||
# For M1 chip
|
||||
# wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
|
||||
sh Miniconda3-latest-MacOSX*
|
||||
source ~/.zashrc
|
||||
conda create -n funasr python=3.8
|
||||
conda activate funasr
|
||||
```
|
||||
#### Windows
|
||||
Ref to [docs](https://docs.conda.io/en/latest/miniconda.html#windows-installers)
|
||||
|
||||
### 安装Pytorch（版本 >= 1.11.0）：
|
||||
|
||||
```sh
|
||||
pip3 install torch torchaudio
|
||||
```
|
||||
如果您的环境中存在CUDAs，则应安装与CUDA匹配版本的pytorch，匹配列表可在文档中找到（[文档](https://pytorch.org/get-started/previous-versions/)）。
|
||||
### 安装funasr
|
||||
|
||||
#### 从pip安装
|
||||
|
||||
```shell
|
||||
pip3 install -U funasr
|
||||
# 对于中国大陆用户，可以使用以下命令进行安装：
|
||||
# pip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
#### 或者从源代码安装
|
||||
|
||||
``` sh
|
||||
git clone https://github.com/alibaba/FunASR.git && cd FunASR
|
||||
pip3 install -e ./
|
||||
# 对于中国大陆用户，可以使用以下命令进行安装：
|
||||
# pip3 install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
### 安装modelscope（可选）
|
||||
|
||||
如果您想要使用ModelScope中的预训练模型，则应安装modelscope:
|
||||
|
||||
```shell
|
||||
pip3 install -U modelscope
|
||||
# 对于中国大陆用户，可以使用以下命令进行安装：
|
||||
# pip3 install -U modelscope -i https://mirror.sjtu.edu.cn/pypi/web/simple
|
||||
```
|
||||
|
||||
### 常见问题解答
|
||||
- 在MAC M1芯片上安装时，可能会出现以下错误：
|
||||
- - _cffi_backend.cpython-38-darwin.so' (mach-o file, but is an incompatible architecture (have (x86_64), need (arm64e)))
|
||||
```shell
|
||||
pip uninstall cffi pycparser
|
||||
ARCHFLAGS="-arch arm64" pip install cffi pycparser --compile --no-cache-dir
|
||||
```
|
||||
@@ -0,0 +1,38 @@
|
||||
# Baseline
|
||||
## Overview
|
||||
We will release an E2E SA-ASR baseline conducted on [FunASR](https://github.com/alibaba-damo-academy/FunASR) at the time according to the timeline. The model architecture is shown in Figure 3. The SpeakerEncoder is initialized with a pre-trained speaker verification model from ModelScope. This speaker verification model is also be used to extract the speaker embedding in the speaker profile.
|
||||
|
||||
|
||||
|
||||
## Quick start
|
||||
To run the baseline, first you need to install FunASR and ModelScope. ([installation](https://github.com/alibaba-damo-academy/FunASR#installation))
|
||||
There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.
|
||||
Before running `run.sh`, you must manually download and unpack the [AliMeeting](http://www.openslr.org/119/) corpus and place it in the `./dataset` directory:
|
||||
```shell
|
||||
dataset
|
||||
|—— Eval_Ali_far
|
||||
|—— Eval_Ali_near
|
||||
|—— Test_Ali_far
|
||||
|—— Test_Ali_near
|
||||
|—— Train_Ali_far
|
||||
|—— Train_Ali_near
|
||||
```
|
||||
Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
|
||||
```shell
|
||||
data/Test_2023_Ali_far
|
||||
|—— wav.scp
|
||||
|—— wav_raw.scp
|
||||
|—— segments
|
||||
|—— utt2spk
|
||||
|—— spk2utt
|
||||
```
|
||||
For more details you can see [here](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs/alimeeting/sa-asr/README.md)
|
||||
|
||||
## Baseline results
|
||||
The results of the baseline system are shown in Table 3. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
|
||||
|
||||
|
||||
| |SI-CER(%) |cpCER(%) |
|
||||
|:---------------|:------------:|----------:|
|
||||
|oracle profile |32.72 |42.92 |
|
||||
|cluster profile|32.73 |49.37 |
|
||||
@@ -0,0 +1,14 @@
|
||||
# Challenge Result
|
||||
The following table shows the final results of the competition, where Sub-track1 represents the sub-track under fixed training condition and Sub-track 2 represents the sub-track under the open training condition. All result in this table is cp-CER (%). The rankings in the table are the combined rankings of the two sub-tracks as all teams' submissions met the requirements of the sub-track under fixed training condition.
|
||||
| Rank | Team Name | Sub-track1 | Sub-track2 | paper |
|
||||
|------|----------------------|------------|------------|------------------------|
|
||||
| 1 | Ximalaya Speech Team | 11.27 | 11.27 | |
|
||||
| 2 | 小马达 | 18.64 | 18.64 | |
|
||||
| 3 | AIzyzx | 22.83 | 22.83 | |
|
||||
| 4 | AsrSpeeder | / | 23.51 | |
|
||||
| 5 | zyxlhz | 24.82 | 24.82 | |
|
||||
| 6 | CMCAI | 26.11 | / | |
|
||||
| 7 | Volcspeech | 34.21 | 34.21 | |
|
||||
| 8 | 鉴往知来 | 40.14 | 40.14 | |
|
||||
| 9 | baseline | 41.55 | 41.55 | |
|
||||
| 10 | DAICT | 41.64 | | |
|
||||
@@ -0,0 +1,4 @@
|
||||
# Contact
|
||||
If you have any questions about M2MeT2.0 challenge, please contact us by
|
||||
|
||||
- email: [m2met.alimeeting@gmail.com](mailto:m2met.alimeeting@gmail.com)
|
||||
@@ -0,0 +1,26 @@
|
||||
# Datasets
|
||||
## Overview of training data
|
||||
In the fixed training condition, the training dataset is restricted to three publicly available corpora, namely, AliMeeting, AISHELL-4, and CN-Celeb. To evaluate the performance of the models trained on these datasets, we will release a new Test set called Test-2023 for scoring and ranking. We will describe the AliMeeting dataset and the Test-2023 set in detail.
|
||||
## Detail of AliMeeting corpus
|
||||
AliMeeting contains 118.75 hours of speech data in total. The dataset is divided into 104.75 hours for training (Train), 4 hours for evaluation (Eval) and 10 hours as test set (Test) for scoring and ranking. Specifically, the Train, Eval and Test sets contain 212, 8 and 20 sessions, respectively. Each session consists of a 15 to 30-minute discussion by a group of participants. The total number of participants in Train, Eval and Test sets is 456, 25 and 60, respectively, with balanced gender coverage.
|
||||
|
||||
The dataset is collected in 13 meeting venues, which are categorized into three types: small, medium, and large rooms with sizes ranging from 8 m$^{2}$ to 55 m$^{2}$. Different rooms give us a variety of acoustic properties and layouts. The detailed parameters of each meeting venue will be released together with the Train data. The type of wall material of the meeting venues covers cement, glass, etc. Other furnishings in meeting venues include sofa, TV, blackboard, fan, air conditioner, plants, etc. During recording, the participants of the meeting sit around the microphone array which is placed on the table and conduct a natural conversation. The microphone-speaker distance ranges from 0.3 m to 5.0 m. All participants are native Chinese speakers speaking Mandarin without strong accents. During the meeting, various kinds of indoor noise including but not limited to clicking, keyboard, door opening/closing, fan, bubble noise, etc., are made naturally. For both Train and Eval sets, the participants are required to remain in the same position during recording. There is no speaker overlap between the Train and Eval set. An example of the recording venue from the Train set is shown in Fig 1.
|
||||
|
||||
|
||||
|
||||
The number of participants within one meeting session ranges from 2 to 4. To ensure the coverage of different overlap ratios, we select various meeting topics during recording, including medical treatment, education, business, organization management, industrial production and other daily routine meetings. The average speech overlap ratio of Train, Eval and Test sets are 42.27\%, 34.76\% and 42.8\%, respectively. More details of AliMeeting are shown in Table 1. A detailed overlap ratio distribution of meeting sessions with different numbers of speakers in the Train, Eval and Test set is shown in Table 2.
|
||||
|
||||
|
||||
|
||||
The Test-2023 set consists of 20 sessions that were recorded in an identical acoustic setting to that of the AliMeeting corpus. Each meeting session in the Test-2023 dataset comprises between 2 and 4 participants, thereby sharing a similar configuration with the AliMeeting test set.
|
||||
|
||||
We also record the near-field signal of each participant using a headset microphone and ensure that only the participant's own speech is recorded and transcribed. It is worth noting that the far-field audio recorded by the microphone array and the near-field audio recorded by the headset microphone will be synchronized to a common timeline range.
|
||||
|
||||
All transcriptions of the speech data are prepared in TextGrid format for each session, which contains the information of the session duration, speaker information (number of speaker, speaker-id, gender, etc.), the total number of segments of each speaker, the timestamp and transcription of each segment, etc.
|
||||
## Get the data
|
||||
The three dataset for training mentioned above can be downloaded at [OpenSLR](https://openslr.org/resources.php). The participants can download via the following links. Particularly, in the baseline we provide convenient data preparation scripts for AliMeeting corpus.
|
||||
- [AliMeeting](https://openslr.org/119/)
|
||||
- [AISHELL-4](https://openslr.org/111/)
|
||||
- [CN-Celeb](https://openslr.org/82/)
|
||||
|
||||
Now, the new test set is available [here](https://speech-lab-share-data.oss-cn-shanghai.aliyuncs.com/AliMeeting/openlr/Test_2023_Ali.tar.gz)
|
||||
@@ -0,0 +1,28 @@
|
||||
# Introduction
|
||||
## Call for participation
|
||||
Automatic speech recognition (ASR) and speaker diarization have made significant strides in recent years, resulting in a surge of speech technology applications across various domains. However, meetings present unique challenges to speech technologies due to their complex acoustic conditions and diverse speaking styles, including overlapping speech, variable numbers of speakers, far-field signals in large conference rooms, and environmental noise and reverberation.
|
||||
|
||||
Over the years, several challenges have been organized to advance the development of meeting transcription, including the Rich Transcription evaluation and Computational Hearing in Multisource Environments (CHIME) challenges. The latest iteration of the CHIME challenge has a particular focus on distant automatic speech recognition and developing systems that can generalize across various array topologies and application scenarios. However, while progress has been made in English meeting transcription, language differences remain a significant barrier to achieving comparable results in non-English languages, such as Mandarin. The Multimodal Information Based Speech Processing (MISP) and Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenges have been instrumental in advancing Mandarin meeting transcription. The MISP challenge seeks to address the problem of audio-visual distant multi-microphone signal processing in everyday home environments, while the M2MeT challenge focuses on tackling the speech overlap issue in offline meeting rooms.
|
||||
|
||||
The ICASSP2022 M2MeT challenge focuses on meeting scenarios, and it comprises two main tasks: speaker diarization and multi-speaker automatic speech recognition. The former involves identifying who spoke when in the meeting, while the latter aims to transcribe speech from multiple speakers simultaneously, which poses significant technical difficulties due to overlapping speech and acoustic interferences.
|
||||
|
||||
Building on the success of the previous M2MeT challenge, we are excited to propose the M2MeT2.0 challenge as an ASRU 2023 challenge special session. In the original M2MeT challenge, the evaluation metric was speaker-independent, which meant that the transcription could be determined, but not the corresponding speaker. To address this limitation and further advance the current multi-talker ASR system towards practicality, the M2MeT2.0 challenge proposes the speaker-attributed ASR task with two sub-tracks: fixed and open training conditions. The speaker-attribute automatic speech recognition (ASR) task aims to tackle the practical and challenging problem of identifying "who spoke what at when". To facilitate reproducible research in this field, we offer a comprehensive overview of the dataset, rules, evaluation metrics, and baseline systems. Furthermore, we will release a carefully curated test set, comprising approximately 10 hours of audio, according to the timeline. The new test set is designed to enable researchers to validate and compare their models' performance and advance the state of the art in this area.
|
||||
|
||||
## Timeline(AOE Time)
|
||||
- $ April~29, 2023: $ Challenge and registration open.
|
||||
- $ May~11, 2023: $ Baseline release.
|
||||
- $ May~22, 2023: $ Registration deadline, the due date for participants to join the Challenge.
|
||||
- $ June~16, 2023: $ Test data release and leaderboard open.
|
||||
- $ June~20, 2023: $ Final submission deadline and leaderboar close.
|
||||
- $ June~26, 2023: $ Evaluation result and ranking release.
|
||||
- $ July~3, 2023: $ Deadline for paper submission.
|
||||
- $ July~10, 2023: $ Deadline for final paper submission.
|
||||
- $ December~12\ to\ 16, 2023: $ ASRU Workshop and Challenge Session.
|
||||
|
||||
## Guidelines
|
||||
|
||||
Interested participants, whether from academia or industry, must register for the challenge by completing the Google form below. The deadline for registration is May 22, 2023.
|
||||
|
||||
[M2MeT2.0 Registration](https://docs.google.com/forms/d/e/1FAIpQLSf77T9vAl7Ym-u5g8gXu18SBofoWRaFShBo26Ym0-HDxHW9PQ/viewform?usp=sf_link)
|
||||
|
||||
Within three working days, the challenge organizer will send email invitations to eligible teams to participate in the challenge. All qualified teams are required to adhere to the challenge rules, which will be published on the challenge page. Prior to the ranking release time, each participant must submit a system description document detailing their approach and methods. The organizer will select the top ranking submissions to be included in the ASRU2023 Proceedings.
|
||||
@@ -0,0 +1,20 @@
|
||||
# Minimal makefile for Sphinx documentation
|
||||
#
|
||||
|
||||
# You can set these variables from the command line, and also
|
||||
# from the environment for the first two.
|
||||
SPHINXOPTS ?=
|
||||
SPHINXBUILD ?= sphinx-build
|
||||
SOURCEDIR = .
|
||||
BUILDDIR = _build
|
||||
|
||||
# Put it first so that "make" without argument is like "make help".
|
||||
help:
|
||||
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
|
||||
.PHONY: help Makefile
|
||||
|
||||
# Catch-all target: route all unknown targets to Sphinx using the new
|
||||
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
|
||||
%: Makefile
|
||||
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
@@ -0,0 +1,48 @@
|
||||
# Organizers
|
||||
***Lei Xie, Professor, AISHELL foundation, China***
|
||||
|
||||
Email: [lxie@nwpu.edu.cn](mailto:lxie@nwpu.edu.cn)
|
||||
|
||||
<img src="images/lxie.jpeg" alt="lxie" width="20%">
|
||||
|
||||
|
||||
***Kong Aik Lee, Senior Scientist at Institute for Infocomm Research, A\*Star, Singapore***
|
||||
|
||||
Email: [kongaik.lee@ieee.org](mailto:kongaik.lee@ieee.org)
|
||||
|
||||
<img src="images/kong.png" alt="kong" width="20%">
|
||||
|
||||
|
||||
***Zhijie Yan, Principal Engineer at Alibaba, China***
|
||||
Email: [zhijie.yzj@alibaba-inc.com](mailto:zhijie.yzj@alibaba-inc.com)
|
||||
|
||||
<img src="images/zhijie.jpg" alt="zhijie" width="20%">
|
||||
|
||||
***Shiliang Zhang, Senior Engineer at Alibaba, China***
|
||||
Email: [sly.zsl@alibaba-inc.com](mailto:sly.zsl@alibaba-inc.com)
|
||||
|
||||
<img src="images/zsl.JPG" alt="zsl" width="20%">
|
||||
|
||||
***Yanmin Qian, Professor, Shanghai Jiao Tong University, China***
|
||||
|
||||
Email: [yanminqian@sjtu.edu.cn](mailto:yanminqian@sjtu.edu.cn)
|
||||
|
||||
<img src="images/qian.jpeg" alt="qian" width="20%">
|
||||
|
||||
***Zhuo Chen, Applied Scientist in Microsoft, USA***
|
||||
|
||||
Email: [zhuc@microsoft.com](mailto:zhuc@microsoft.com)
|
||||
|
||||
<img src="images/chenzhuo.jpg" alt="chenzhuo" width="20%">
|
||||
|
||||
***Jian Wu, Applied Scientist in Microsoft, USA***
|
||||
|
||||
Email: [wujian@microsoft.com](mailto:wujian@microsoft.com)
|
||||
|
||||
<img src="images/wujian.jpg" alt="wujian" width="20%">
|
||||
|
||||
***Hui Bu, CEO, AISHELL foundation, China***
|
||||
|
||||
Email: [buhui@aishelldata.com](mailto:buhui@aishelldata.com)
|
||||
|
||||
<img src="images/buhui.jpeg" alt="buhui" width="20%">
|
||||
@@ -0,0 +1,14 @@
|
||||
# Rules
|
||||
All participants should adhere to the following rules to be eligible for the challenge.
|
||||
|
||||
- Data augmentation is allowed on the original training dataset, including, but not limited to, adding noise or reverberation, speed perturbation and tone change.
|
||||
|
||||
- Participants are permitted to use the Eval set for model training, but it is not allowed to use the Test set for this purpose. Instead, the Test set should only be utilized for parameter tuning and model selection. Any use of the Test-2023 dataset that violates these rules is strictly prohibited, including but not limited to the use of the Test set for fine-tuning or training the model.
|
||||
|
||||
- If the cpCER of the two systems on the Test dataset are the same, the system with lower computation complexity will be judged as the superior one.
|
||||
|
||||
- If the forced alignment is used to obtain the frame-level classification label, the forced alignment model must be trained on the basis of the data allowed by the corresponding sub-track.
|
||||
|
||||
- Shallow fusion is allowed to the end-to-end approaches, e.g., LAS, RNNT and Transformer, but the training data of the shallow fusion language model can only come from the transcripts of the allowed training dataset.
|
||||
|
||||
- The right of final interpretation belongs to the organizer. In case of special circumstances, the organizer will coordinate the interpretation.
|
||||
@@ -0,0 +1,17 @@
|
||||
# Track & Evaluation
|
||||
## Speaker-Attributed ASR
|
||||
The speaker-attributed ASR task poses a unique challenge of transcribing speech from multiple speakers and assigning a speaker label to the transcription. Figure 2 illustrates the difference between the speaker-attributed ASR task and the multi-speaker ASR task. This track allows for the use of the AliMeeting, Aishell4, and Cn-Celeb datasets as constrained data sources during both training and evaluation. The AliMeeting dataset, which was used in the M2MeT challenge, includes Train, Eval, and Test sets. Additionally, a new Test-2023 set, consisting of approximately 10 hours of meeting data recorded in an identical acoustic setting as the AliMeeting corpus, will be released soon for challenge scoring and ranking. It's worth noting that the organizers will not provide the near-field audio, transcriptions, or oracle timestamps of the Test-2023 set. Instead, segments containing multiple speakers will be provided, which can be obtained using a simple voice activity detection (VAD) model.
|
||||
|
||||
|
||||
|
||||
## Evaluation metric
|
||||
The accuracy of a speaker-attributed ASR system is evaluated using the concatenated minimum permutation character error rate (cpCER) metric. The calculation of cpCER involves three steps. Firstly, the reference and hypothesis transcriptions from each speaker in a session are concatenated in chronological order. Secondly, the character error rate (CER) is calculated between the concatenated reference and hypothesis transcriptions, and this process is repeated for all possible speaker permutations. Finally, the permutation with the lowest CER is selected as the cpCER for that session. TThe CER is obtained by dividing the total number of insertions (Ins), substitutions (Sub), and deletions(Del) of characters required to transform the ASR output into the reference transcript by the total number of characters in the reference transcript. Specifically, CER is calculated by:
|
||||
|
||||
$$\text{CER} = \frac {\mathcal N_{\text{Ins}} + \mathcal N_{\text{Sub}} + \mathcal N_{\text{Del}} }{\mathcal N_{\text{Total}}} \times 100\%,$$
|
||||
|
||||
where $\mathcal N_{\text{Ins}}$, $\mathcal N_{\text{Sub}}$, $\mathcal N_{\text{Del}}$ are the character number of the three errors, and $\mathcal N_{\text{Total}}$ is the total number of characters.
|
||||
## Sub-track arrangement
|
||||
### Sub-track I (Fixed Training Condition):
|
||||
Participants are required to use only the fixed-constrained data (i.e., AliMeeting, Aishell-4, and CN-Celeb) for system development. The usage of any additional data is strictly prohibited. However, participants can use open-source pre-trained models from third-party sources, such as [Hugging Face](https://huggingface.co/models) and [ModelScope](https://www.modelscope.cn/models), provided that the list of utilized models is clearly stated in the final system description paper.
|
||||
### Sub-track II (Open Training Condition):
|
||||
Participants are allowed to use any publicly available data set, privately recorded data, and manual simulation to build their systems in addition to the fixed-constrained data. They can also utilize any open-source pre-trained models, but it is mandatory to provide a clear list of the data and models used in the final system description paper. If manually simulated data is used, a detailed description of the data simulation scheme must be provided.
|
||||
@@ -0,0 +1,44 @@
|
||||
# Configuration file for the Sphinx documentation builder.
|
||||
#
|
||||
# For the full list of built-in configuration values, see the documentation:
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
|
||||
|
||||
project = "MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0"
|
||||
copyright = "2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University"
|
||||
author = "Speech Lab, Alibaba Group; Audio, Speech and Language Processing Group, Northwestern Polytechnical University"
|
||||
|
||||
|
||||
extensions = [
|
||||
"nbsphinx",
|
||||
"sphinx.ext.autodoc",
|
||||
"sphinx.ext.napoleon",
|
||||
"sphinx.ext.viewcode",
|
||||
"sphinx.ext.mathjax",
|
||||
"sphinx.ext.todo",
|
||||
# "sphinxarg.ext",
|
||||
"sphinx_markdown_tables",
|
||||
# 'recommonmark',
|
||||
"sphinx_rtd_theme",
|
||||
"myst_parser",
|
||||
]
|
||||
|
||||
myst_enable_extensions = [
|
||||
"colon_fence",
|
||||
"deflist",
|
||||
"dollarmath",
|
||||
"html_image",
|
||||
]
|
||||
|
||||
myst_heading_anchors = 2
|
||||
myst_highlight_code_blocks = True
|
||||
myst_update_mathjax = False
|
||||
|
||||
templates_path = ["_templates"]
|
||||
source_suffix = [".rst", ".md"]
|
||||
|
||||
pygments_style = "sphinx"
|
||||
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 166 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 232 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 4.4 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 610 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 39 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 991 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 748 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 76 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 2.3 MiB |
@@ -0,0 +1,26 @@
|
||||
.. m2met2 documentation master file, created by
|
||||
sphinx-quickstart on Tue Apr 11 14:18:55 2023.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)
|
||||
==================================================================================
|
||||
Building on the success of the M2MeT challenge, we are delighted to propose the M2MeT2.0 challenge as a special session at ASRU2023.
|
||||
To advance the current state-of-the-art in multi-talker automatic speech recognition, the M2MeT2.0 challenge proposes a speaker-attributed ASR task, comprising two sub-tracks: fixed and open training conditions.
|
||||
To facilitate reproducible research, we provide a comprehensive overview of the dataset, challenge rules, evaluation metrics, and baseline systems.
|
||||
|
||||
Now the new test set contains about 10 hours audio is available. You can download from `here <https://speech-lab-share-data.oss-cn-shanghai.aliyuncs.com/AliMeeting/openlr/Test_2023_Ali.tar.gz>`_
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Contents:
|
||||
|
||||
./Introduction
|
||||
./Dataset
|
||||
./Track_setting_and_evaluation
|
||||
./Baseline
|
||||
./Rules
|
||||
./Challenge_result
|
||||
./Organizers
|
||||
./Contact
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=.
|
||||
set BUILDDIR=_build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
@@ -0,0 +1,35 @@
|
||||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=source
|
||||
set BUILDDIR=build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
@@ -0,0 +1,22 @@
|
||||
# FQA
|
||||
|
||||
## How to use VAD model by modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/236)
|
||||
|
||||
## How to use Punctuation model by modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
|
||||
|
||||
## How to use Parafomrer model for streaming by modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
|
||||
|
||||
## How to use vad, asr and punc model by modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/278)
|
||||
|
||||
## How to combine vad, asr, punc and nnlm models inside modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/134)
|
||||
|
||||
## How to combine timestamp prediction model by modelscope pipeline
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/246)
|
||||
|
||||
## How to switch decoding mode between online and offline for UniASR model
|
||||
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
|
||||
@@ -0,0 +1,5 @@
|
||||
## Audio Cut
|
||||
|
||||
## Realtime Speech Recognition
|
||||
|
||||
## Audio Chat
|
||||
@@ -0,0 +1,125 @@
|
||||
# Build custom tasks
|
||||
FunASR is similar to ESPNet, which applies `Task` as the general interface ti achieve the training and inference of models. Each `Task` is a class inherited from `AbsTask` and its corresponding code can be seen in `funasr/tasks/abs_task.py`. The main functions of `AbsTask` are shown as follows:
|
||||
```python
|
||||
class AbsTask(ABC):
|
||||
@classmethod
|
||||
def add_task_arguments(cls, parser: argparse.ArgumentParser):
|
||||
pass
|
||||
|
||||
@classmethod
|
||||
def build_preprocess_fn(cls, args, train):
|
||||
(...)
|
||||
|
||||
@classmethod
|
||||
def build_collate_fn(cls, args: argparse.Namespace):
|
||||
(...)
|
||||
|
||||
@classmethod
|
||||
def build_model(cls, args):
|
||||
(...)
|
||||
|
||||
@classmethod
|
||||
def main(cls, args):
|
||||
(...)
|
||||
```
|
||||
- add_task_arguments：Add parameters required by a specified `Task`
|
||||
- build_preprocess_fn：定义如何处理对样本进行预处理 define how to preprocess samples
|
||||
- build_collate_fn：define how to combine multiple samples into a `batch`
|
||||
- build_model：define the model
|
||||
- main：training interface, starting training through `Task.main()`
|
||||
|
||||
Next, we take the speech recognition as an example to introduce how to define a new `Task`. For the corresponding code, please see `ASRTask` in `funasr/tasks/asr.py`. The procedure of defining a new `Task` is actually the procedure of redefining the above functions according to the requirements of the specified `Task`.
|
||||
|
||||
- add_task_arguments
|
||||
```python
|
||||
@classmethod
|
||||
def add_task_arguments(cls, parser: argparse.ArgumentParser):
|
||||
group = parser.add_argument_group(description="Task related")
|
||||
group.add_argument(
|
||||
"--token_list",
|
||||
type=str_or_none,
|
||||
default=None,
|
||||
help="A text mapping int-id to token",
|
||||
)
|
||||
(...)
|
||||
```
|
||||
For speech recognition tasks, specific parameters required include `token_list`, etc. According to the specific requirements of different tasks, users can define corresponding parameters in this function.
|
||||
|
||||
- build_preprocess_fn
|
||||
```python
|
||||
@classmethod
|
||||
def build_preprocess_fn(cls, args, train):
|
||||
if args.use_preprocessor:
|
||||
retval = CommonPreprocessor(
|
||||
train=train,
|
||||
token_type=args.token_type,
|
||||
token_list=args.token_list,
|
||||
bpemodel=args.bpemodel,
|
||||
non_linguistic_symbols=args.non_linguistic_symbols,
|
||||
text_cleaner=args.cleaner,
|
||||
...
|
||||
)
|
||||
else:
|
||||
retval = None
|
||||
return retval
|
||||
```
|
||||
This function defines how to preprocess samples. Specifically, the input of speech recognition tasks includes speech and text. For speech, functions such as (optional) adding noise and reverberation to the speech are supported. For text, functions such as (optional) processing text according to bpe and mapping text to `tokenid` are supported. Users can choose the preprocessing operation that needs to be performed on the sample. For the detail implementation, please refer to `CommonPreprocessor`.
|
||||
|
||||
- build_collate_fn
|
||||
```python
|
||||
@classmethod
|
||||
def build_collate_fn(cls, args, train):
|
||||
return CommonCollateFn(float_pad_value=0.0, int_pad_value=-1)
|
||||
```
|
||||
This function defines how to combine multiple samples into a `batch`. For speech recognition tasks, `padding` is employed to obtain equal-length data from different speech and text. Specifically, we set `0.0` as the default padding value for speech and `-1` as the default padding value for text. Users can define different `batch` operations here. For the detail implementation, please refer to `CommonCollateFn`.
|
||||
|
||||
- build_model
|
||||
```python
|
||||
@classmethod
|
||||
def build_model(cls, args, train):
|
||||
with open(args.token_list, encoding="utf-8") as f:
|
||||
token_list = [line.rstrip() for line in f]
|
||||
vocab_size = len(token_list)
|
||||
frontend = frontend_class(**args.frontend_conf)
|
||||
specaug = specaug_class(**args.specaug_conf)
|
||||
normalize = normalize_class(**args.normalize_conf)
|
||||
preencoder = preencoder_class(**args.preencoder_conf)
|
||||
encoder = encoder_class(input_size=input_size, **args.encoder_conf)
|
||||
postencoder = postencoder_class(input_size=encoder_output_size, **args.postencoder_conf)
|
||||
decoder = decoder_class(vocab_size=vocab_size, encoder_output_size=encoder_output_size, **args.decoder_conf)
|
||||
ctc = CTC(odim=vocab_size, encoder_output_size=encoder_output_size, **args.ctc_conf)
|
||||
model = model_class(
|
||||
vocab_size=vocab_size,
|
||||
frontend=frontend,
|
||||
specaug=specaug,
|
||||
normalize=normalize,
|
||||
preencoder=preencoder,
|
||||
encoder=encoder,
|
||||
postencoder=postencoder,
|
||||
decoder=decoder,
|
||||
ctc=ctc,
|
||||
token_list=token_list,
|
||||
**args.model_conf,
|
||||
)
|
||||
return model
|
||||
```
|
||||
This function defines the detail of the model. For different speech recognition models, the same speech recognition `Task` can usually be shared and the remaining thing needed to be done is to define a specific model in this function. For example, a speech recognition model with a standard encoder-decoder structure has been shown above. Specifically, it first defines each module of the model, including encoder, decoder, etc. and then combine these modules together to generate a complete model. In FunASR, the model needs to inherit `FunASRModel` and the corresponding code can be seen in `funasr/train/abs_espnet_model.py`. The main function needed to be implemented is the `forward` function.
|
||||
|
||||
Next, we take `SANMEncoder` as an example to introduce how to use a custom encoder as a part of the model when defining the specified model and the corresponding code can be seen in `funasr/models/encoder/sanm_encoder.py`. For a custom encoder, in addition to inheriting the common encoder class `AbsEncoder`, it is also necessary to define the `forward` function to achieve the forward computation of the `encoder`. After defining the `encoder`, it should also be registered in the `Task`. The corresponding code example can be seen as below:
|
||||
```python
|
||||
encoder_choices = ClassChoices(
|
||||
"encoder",
|
||||
classes=dict(
|
||||
conformer=ConformerEncoder,
|
||||
transformer=TransformerEncoder,
|
||||
rnn=RNNEncoder,
|
||||
sanm=SANMEncoder,
|
||||
sanm_chunk_opt=SANMEncoderChunkOpt,
|
||||
data2vec_encoder=Data2VecEncoder,
|
||||
mfcca_enc=MFCCAEncoder,
|
||||
),
|
||||
type_check=AbsEncoder,
|
||||
default="rnn",
|
||||
)
|
||||
```
|
||||
In this code, `sanm=SANMEncoder` takes the newly defined `SANMEncoder` as an optional choice of the `encoder`. Once the user specifies the `encoder` as `sanm` in the configuration file, the `SANMEncoder` will be correspondingly employed as the `encoder` module of the model.
|
||||
@@ -0,0 +1,38 @@
|
||||
# Papers
|
||||
|
||||
FunASR have implemented the following paper code
|
||||
|
||||
### Speech Recognition
|
||||
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://arxiv.org/abs/2305.11013), INTERSPEECH 2023
|
||||
- [BAT: Boundary aware transducer for memory-efficient and low-latency ASR](https://arxiv.org/abs/2305.11571), INTERSPEECH 2023
|
||||
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://arxiv.org/abs/2206.08317), INTERSPEECH 2022
|
||||
- [E-branchformer: Branchformer with enhanced merging for speech recognition](https://arxiv.org/abs/2210.00077), SLT 2022
|
||||
- [Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding](https://proceedings.mlr.press/v162/peng22a.html?ref=https://githubhelp.com), ICML 2022
|
||||
- [Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model](https://arxiv.org/abs/2010.14099), arXiv preprint arXiv:2010.14099, 2020
|
||||
- [San-m: Memory equipped self-attention for end-to-end speech recognition](https://arxiv.org/pdf/2006.01713), INTERSPEECH 2020
|
||||
- [Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition](https://arxiv.org/abs/2006.01712), INTERSPEECH 2020
|
||||
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100), INTERSPEECH 2020
|
||||
- [Sequence-to-sequence learning with Transducers](https://arxiv.org/pdf/1211.3711.pdf), NIPS 2016
|
||||
|
||||
|
||||
### Multi-talker Speech Recognition
|
||||
- [MFCCA:Multi-Frame Cross-Channel attention for multi-speaker ASR in Multi-party meeting scenario](https://arxiv.org/abs/2210.05265), ICASSP 2022
|
||||
|
||||
### Voice Activity Detection
|
||||
- [Deep-FSMN for Large Vocabulary Continuous Speech Recognition](https://arxiv.org/abs/1803.05030), ICASSP 2018
|
||||
|
||||
### Punctuation Restoration
|
||||
- [CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection](https://arxiv.org/pdf/2003.01309.pdf), ICASSP 2018
|
||||
|
||||
### Language Models
|
||||
- [Attention Is All You Need](https://arxiv.org/abs/1706.03762), NEURIPS 2017
|
||||
|
||||
### Speaker Verification
|
||||
- [X-VECTORS: ROBUST DNN EMBEDDINGS FOR SPEAKER RECOGNITION](https://www.danielpovey.com/files/2018_icassp_xvectors.pdf), ICASSP 2018
|
||||
|
||||
### Speaker diarization
|
||||
- [Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis](https://arxiv.org/abs/2211.10243), EMNLP 2022
|
||||
- [TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization](https://arxiv.org/abs/2303.05397), ICASSP 2023
|
||||
|
||||
### Timestamp Prediction
|
||||
- [Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model](https://arxiv.org/abs/2301.12343), arXiv:2301.12343
|
||||
@@ -0,0 +1,424 @@
|
||||
([简体中文](./README_zh.md)|English)
|
||||
|
||||
FunASR has open-sourced a large number of pre-trained models on industrial data. You are free to use, copy, modify, and share FunASR models under the [Model License Agreement](https://github.com/alibaba-damo-academy/FunASR/blob/main/MODEL_LICENSE). Below, we list some representative models. For a comprehensive list, please refer to our [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo).
|
||||
|
||||
<div align="center">
|
||||
<h4>
|
||||
<a href="#Inference"> Model Inference </a>
|
||||
｜<a href="#Training"> Model Training and Testing </a>
|
||||
｜<a href="#Export"> Model Export and Testing </a>
|
||||
</h4>
|
||||
</div>
|
||||
|
||||
<a name="Inference"></a>
|
||||
## Model Inference
|
||||
|
||||
### Quick Start
|
||||
|
||||
For command-line invocation:
|
||||
```shell
|
||||
funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
|
||||
```
|
||||
|
||||
For python code invocation (recommended):
|
||||
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="paraformer-zh")
|
||||
|
||||
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
|
||||
print(res)
|
||||
```
|
||||
|
||||
### API Description
|
||||
#### AutoModel Definition
|
||||
```python
|
||||
model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch_size=[int], hub=[str], **kwargs)
|
||||
```
|
||||
- `model`(str): model name in the [Model Repository](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo), or a model path on local disk.
|
||||
- `device`(str): `cuda:0` (default gpu0) for using GPU for inference, specify `cpu` for using CPU.
|
||||
- `ncpu`(int): `4` (default), sets the number of threads for CPU internal operations.
|
||||
- `output_dir`(str): `None` (default), set this to specify the output path for the results.
|
||||
- `batch_size`(int): `1` (default), the number of samples per batch during decoding.
|
||||
- `hub`(str)：`ms` (default) to download models from ModelScope. Use `hf` to download models from Hugging Face.
|
||||
- `**kwargs`(dict): Any parameters found in config.yaml can be directly specified here, for instance, the maximum segmentation length in the vad model max_single_segment_time=6000 (milliseconds).
|
||||
|
||||
#### AutoModel Inference
|
||||
```python
|
||||
res = model.generate(input=[str], output_dir=[str])
|
||||
```
|
||||
- `input`: The input to be decoded, which could be:
|
||||
- A wav file path, e.g., asr_example.wav
|
||||
- A pcm file path, e.g., asr_example.pcm, in this case, specify the audio sampling rate fs (default is 16000)
|
||||
- An audio byte stream, e.g., byte data from a microphone
|
||||
- A wav.scp, a Kaldi-style wav list (wav_id \t wav_path), for example:
|
||||
```text
|
||||
asr_example1 ./audios/asr_example1.wav
|
||||
asr_example2 ./audios/asr_example2.wav
|
||||
```
|
||||
When using wav.scp as input, you must set output_dir to save the output results.
|
||||
- Audio samples, `e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, data type is numpy.ndarray. Supports batch inputs, type is list：
|
||||
```[audio_sample1, audio_sample2, ..., audio_sampleN]```
|
||||
- fbank input, supports batch grouping. Shape is [batch, frames, dim], type is torch.Tensor.
|
||||
- `output_dir`: None (default), if set, specifies the output path for the results.
|
||||
- `**kwargs`(dict): Inference parameters related to the model, for example,`beam_size=10`，`decoding_ctc_weight=0.1`.
|
||||
|
||||
|
||||
### More Usage Introduction
|
||||
|
||||
|
||||
#### Speech Recognition (Non-streaming)
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
# paraformer-zh is a multi-functional asr model
|
||||
# use vad, punc, spk or not as you need
|
||||
model = AutoModel(model="paraformer-zh",
|
||||
vad_model="fsmn-vad",
|
||||
vad_kwargs={"max_single_segment_time": 60000},
|
||||
punc_model="ct-punc",
|
||||
# spk_model="cam++"
|
||||
)
|
||||
wav_file = f"{model.model_path}/example/asr_example.wav"
|
||||
res = model.generate(input=wav_file, batch_size_s=300, batch_size_threshold_s=60, hotword='魔搭')
|
||||
print(res)
|
||||
```
|
||||
Notes:
|
||||
- Typically, the input duration for models is limited to under 30 seconds. However, when combined with `vad_model`, support for audio input of any length is enabled, not limited to the paraformer model—any audio input model can be used.
|
||||
- Parameters related to model can be directly specified in the definition of AutoModel; parameters related to `vad_model` can be set through `vad_kwargs`, which is a dict; similar parameters include `punc_kwargs` and `spk_kwargs`.
|
||||
- `max_single_segment_time`: Denotes the maximum audio segmentation length for `vad_model`, measured in milliseconds (ms).
|
||||
- `batch_size_s` represents the use of dynamic batching, where the total audio duration within a batch is measured in seconds (s).
|
||||
- `batch_size_threshold_s`: Indicates that when the duration of an audio segment post-VAD segmentation exceeds the batch_size_threshold_s threshold, the batch size is set to 1, measured in seconds (s).
|
||||
|
||||
Recommendations:
|
||||
|
||||
When you input long audio and encounter Out Of Memory (OOM) issues, since memory usage tends to increase quadratically with audio length, consider the following three scenarios:
|
||||
|
||||
a) At the beginning of inference, memory usage primarily depends on `batch_size_s`. Appropriately reducing this value can decrease memory usage.
|
||||
b) During the middle of inference, when encountering long audio segments cut by VAD and the total token count is less than `batch_size_s`, yet still facing OOM, you can appropriately reduce `batch_size_threshold_s`. If the threshold is exceeded, the batch size is forced to 1.
|
||||
c) Towards the end of inference, if long audio segments cut by VAD have a total token count less than `batch_size_s` and exceed the `threshold` batch_size_threshold_s, forcing the batch size to 1 and still facing OOM, you may reduce `max_single_segment_time` to shorten the VAD audio segment length.
|
||||
|
||||
#### Speech Recognition (Streaming)
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
|
||||
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
|
||||
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
|
||||
|
||||
model = AutoModel(model="paraformer-zh-streaming")
|
||||
|
||||
import soundfile
|
||||
import os
|
||||
|
||||
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
|
||||
speech, sample_rate = soundfile.read(wav_file)
|
||||
chunk_stride = chunk_size[1] * 960 # 600ms
|
||||
|
||||
cache = {}
|
||||
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
|
||||
for i in range(total_chunk_num):
|
||||
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
|
||||
is_final = i == total_chunk_num - 1
|
||||
res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
|
||||
print(res)
|
||||
```
|
||||
Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.
|
||||
|
||||
#### Voice Activity Detection (Non-Streaming)
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="fsmn-vad")
|
||||
wav_file = f"{model.model_path}/example/vad_example.wav"
|
||||
res = model.generate(input=wav_file)
|
||||
print(res)
|
||||
```
|
||||
Note: The output format of the VAD model is: `[[beg1, end1], [beg2, end2], ..., [begN, endN]]`, where `begN/endN` indicates the starting/ending point of the `N-th` valid audio segment, measured in milliseconds.
|
||||
|
||||
#### Voice Activity Detection (Streaming)
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
chunk_size = 200 # ms
|
||||
model = AutoModel(model="fsmn-vad")
|
||||
|
||||
import soundfile
|
||||
|
||||
wav_file = f"{model.model_path}/example/vad_example.wav"
|
||||
speech, sample_rate = soundfile.read(wav_file)
|
||||
chunk_stride = int(chunk_size * sample_rate / 1000)
|
||||
|
||||
cache = {}
|
||||
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
|
||||
for i in range(total_chunk_num):
|
||||
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
|
||||
is_final = i == total_chunk_num - 1
|
||||
res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
|
||||
if len(res[0]["value"]):
|
||||
print(res)
|
||||
```
|
||||
Note: The output format for the streaming VAD model can be one of four scenarios:
|
||||
- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`：The same as the offline VAD output result mentioned above.
|
||||
- `[[beg, -1]]`：Indicates that only a starting point has been detected.
|
||||
- `[[-1, end]]`：Indicates that only an ending point has been detected.
|
||||
- `[]`：Indicates that neither a starting point nor an ending point has been detected.
|
||||
|
||||
The output is measured in milliseconds and represents the absolute time from the starting point.
|
||||
#### Punctuation Restoration
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="ct-punc")
|
||||
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
|
||||
print(res)
|
||||
```
|
||||
#### Timestamp Prediction
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="fa-zh")
|
||||
wav_file = f"{model.model_path}/example/asr_example.wav"
|
||||
text_file = f"{model.model_path}/example/text.txt"
|
||||
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
|
||||
print(res)
|
||||
```
|
||||
|
||||
More examples ref to [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)
|
||||
|
||||
<a name="Training"></a>
|
||||
## Model Training and Testing
|
||||
|
||||
### Quick Start
|
||||
|
||||
Execute via command line (for quick testing, not recommended):
|
||||
```shell
|
||||
funasr-train ++model=paraformer-zh ++train_data_set_list=data/list/train.jsonl ++valid_data_set_list=data/list/val.jsonl ++output_dir="./outputs" &> log.txt &
|
||||
```
|
||||
|
||||
Execute with Python code (supports multi-node and multi-GPU, recommended):
|
||||
|
||||
```shell
|
||||
cd examples/industrial_data_pretraining/paraformer
|
||||
bash finetune.sh
|
||||
# "log_file: ./outputs/log.txt"
|
||||
```
|
||||
Full code ref to [finetune.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/finetune.sh)
|
||||
|
||||
### Detailed Parameter Description:
|
||||
|
||||
```shell
|
||||
funasr/bin/train.py \
|
||||
++model="${model_name_or_model_dir}" \
|
||||
++train_data_set_list="${train_data}" \
|
||||
++valid_data_set_list="${val_data}" \
|
||||
++dataset_conf.batch_size=20000 \
|
||||
++dataset_conf.batch_type="token" \
|
||||
++dataset_conf.num_workers=4 \
|
||||
++train_conf.max_epoch=50 \
|
||||
++train_conf.log_interval=1 \
|
||||
++train_conf.resume=false \
|
||||
++train_conf.validate_interval=2000 \
|
||||
++train_conf.save_checkpoint_interval=2000 \
|
||||
++train_conf.keep_nbest_models=20 \
|
||||
++train_conf.avg_nbest_model=10 \
|
||||
++optim_conf.lr=0.0002 \
|
||||
++output_dir="${output_dir}" &> ${log_file}
|
||||
```
|
||||
|
||||
- `model`（str）: The name of the model (the ID in the model repository), at which point the script will automatically download the model to local storage; alternatively, the path to a model already downloaded locally.
|
||||
- `train_data_set_list`（str）: The path to the training data, typically in jsonl format, for specific details refer to [examples](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list).
|
||||
- `valid_data_set_list`（str）：The path to the validation data, also generally in jsonl format, for specific details refer to examples](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list).
|
||||
- `dataset_conf.batch_type`（str）：example (default), the type of batch. example means batches are formed with a fixed number of batch_size samples; length or token means dynamic batching, with total length or number of tokens of the batch equalling batch_size.
|
||||
- `dataset_conf.batch_size`（int）：Used in conjunction with batch_type. When batch_type=example, it represents the number of samples; when batch_type=length, it represents the length of the samples, measured in fbank frames (1 frame = 10 ms) or the number of text tokens.
|
||||
- `train_conf.max_epoch`（int）：The total number of epochs for training.
|
||||
- `train_conf.log_interval`（int）：The number of steps between logging.
|
||||
- `train_conf.resume`（int）：Whether to enable checkpoint resuming for training.
|
||||
- `train_conf.validate_interval`（int）：The interval in steps to run validation tests during training.
|
||||
- `train_conf.save_checkpoint_interval`（int）：The interval in steps for saving the model during training.
|
||||
- `train_conf.keep_nbest_models`（int）：The maximum number of model parameters to retain, sorted by validation set accuracy, from highest to lowest.
|
||||
- `train_conf.avg_nbest_model`（int）：Average over the top n models with the highest accuracy.
|
||||
- `optim_conf.lr`（float）：The learning rate.
|
||||
- `output_dir`（str）：The path for saving the model.
|
||||
- `**kwargs`(dict): Any parameters in config.yaml can be specified directly here, for example, to filter out audio longer than 20s: dataset_conf.max_token_length=2000, measured in fbank frames (1 frame = 10 ms) or the number of text tokens.
|
||||
|
||||
#### Multi-GPU Training
|
||||
##### Single-Machine Multi-GPU Training
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 1 --nproc_per_node ${gpu_num} \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
--nnodes represents the total number of participating nodes, while --nproc_per_node indicates the number of processes running on each node.
|
||||
|
||||
##### Multi-Machine Multi-GPU Training
|
||||
|
||||
On the master node, assuming the IP is 192.168.1.1 and the port is 12345, and you're using 2 GPUs, you would run the following command:
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 2 --node_rank 0 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
On the worker node (assuming the IP is 192.168.1.2), you need to ensure that the MASTER_ADDR and MASTER_PORT environment variables are set to match those of the master node, and then run the same command:
|
||||
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 2 --node_rank 1 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
|
||||
--nnodes indicates the total number of nodes participating in the training, --node_rank represents the ID of the current node, and --nproc_per_node specifies the number of processes running on each node (usually corresponds to the number of GPUs).
|
||||
|
||||
#### Data prepare
|
||||
|
||||
`jsonl` ref to（[demo](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）.
|
||||
The instruction scp2jsonl can be used to generate from wav.scp and text.txt. The preparation process for wav.scp and text.txt is as follows:
|
||||
|
||||
`train_text.txt`
|
||||
|
||||
```bash
|
||||
ID0012W0013 当客户风险承受能力评估依据发生变化时
|
||||
ID0012W0014 所有只要处理 data 不管你是做 machine learning 做 deep learning
|
||||
ID0012W0015 he tried to think how it could be
|
||||
```
|
||||
|
||||
|
||||
`train_wav.scp`
|
||||
|
||||
|
||||
```bash
|
||||
BAC009S0764W0121 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav
|
||||
BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav
|
||||
ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
|
||||
```
|
||||
|
||||
`Command`
|
||||
|
||||
```shell
|
||||
# generate train.jsonl and val.jsonl from wav.scp and text.txt
|
||||
scp2jsonl \
|
||||
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
|
||||
++data_type_list='["source", "target"]' \
|
||||
++jsonl_file_out="../../../data/list/train.jsonl"
|
||||
```
|
||||
|
||||
(Optional, not required) If you need to parse from jsonl back to wav.scp and text.txt, you can use the following command:
|
||||
|
||||
```shell
|
||||
# generate wav.scp and text.txt from train.jsonl and val.jsonl
|
||||
jsonl2scp \
|
||||
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
|
||||
++data_type_list='["source", "target"]' \
|
||||
++jsonl_file_in="../../../data/list/train.jsonl"
|
||||
```
|
||||
|
||||
#### Training log
|
||||
|
||||
##### log.txt
|
||||
```shell
|
||||
tail log.txt
|
||||
[2024-03-21 15:55:52,137][root][INFO] - train, rank: 3, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.327), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)], {'data_load': '0.000', 'forward_time': '0.315', 'backward_time': '0.555', 'optim_time': '0.076', 'total_time': '0.947'}, GPU, memory: usage: 3.830 GB, peak: 18.357 GB, cache: 20.910 GB, cache_peak: 20.910 GB
|
||||
[2024-03-21 15:55:52,139][root][INFO] - train, rank: 1, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.334), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.285), ('acc', 0.823), ('loss_pre', 0.046), ('loss', 0.331), ('batch_size', 36)], {'data_load': '0.000', 'forward_time': '0.334', 'backward_time': '0.536', 'optim_time': '0.077', 'total_time': '0.948'}, GPU, memory: usage: 3.943 GB, peak: 18.291 GB, cache: 19.619 GB, cache_peak: 19.619 GB
|
||||
```
|
||||
|
||||
|
||||
- `rank`：gpu id。
|
||||
- `epoch`,`step`,`total step`：the current epoch, step, and total steps.
|
||||
- `loss_avg_rank`：the average loss across all GPUs for the current step.
|
||||
- `loss/ppl/acc_avg_epoch`：the overall average loss/perplexity/accuracy for the current epoch, up to the current step count. The last step of the epoch when it ends represents the total average loss/perplexity/accuracy for that epoch; it is recommended to use the accuracy metric.
|
||||
- `lr`：the learning rate for the current step.
|
||||
- `[('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)]`：the specific data for the current GPU ID.
|
||||
- `total_time`：the total time taken for a single step.
|
||||
- `GPU, memory`：the model-used/peak memory and the model+cache-used/peak memory.
|
||||
|
||||
##### tensorboard
|
||||
```bash
|
||||
tensorboard --logdir /xxxx/FunASR/examples/industrial_data_pretraining/paraformer/outputs/log/tensorboard
|
||||
```
|
||||
http://localhost:6006/
|
||||
|
||||
### 训练后模型测试
|
||||
|
||||
|
||||
#### With `configuration.json` file
|
||||
|
||||
Assuming the training model path is: ./model_dir, if a configuration.json file has been generated in this directory, you only need to change the model name to the model path in the above model inference method.
|
||||
|
||||
For example, for shell inference:
|
||||
```shell
|
||||
python -m funasr.bin.inference ++model="./model_dir" ++input=="${input}" ++output_dir="${output_dir}"
|
||||
```
|
||||
|
||||
Python inference
|
||||
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="./model_dir")
|
||||
|
||||
res = model.generate(input=wav_file)
|
||||
print(res)
|
||||
```
|
||||
|
||||
#### Without `configuration.json` file
|
||||
|
||||
If there is no configuration.json in the model path, you need to manually specify the exact configuration file path and the model path.
|
||||
|
||||
```shell
|
||||
python -m funasr.bin.inference \
|
||||
--config-path "${local_path}" \
|
||||
--config-name "${config}" \
|
||||
++init_param="${init_param}" \
|
||||
++tokenizer_conf.token_list="${tokens}" \
|
||||
++frontend_conf.cmvn_file="${cmvn_file}" \
|
||||
++input="${input}" \
|
||||
++output_dir="${output_dir}" \
|
||||
++device="${device}"
|
||||
```
|
||||
|
||||
Parameter Introduction
|
||||
- `config-path`：This is the path to the config.yaml saved during the experiment, which can be found in the experiment's output directory.
|
||||
- `config-name`：The name of the configuration file, usually config.yaml. It supports both YAML and JSON formats, for example config.json.
|
||||
- `init_param`：The model parameters that need to be tested, usually model.pt. You can choose a specific model file as needed.
|
||||
- `tokenizer_conf.token_list`：The path to the vocabulary file, which is normally specified in config.yaml. There is no need to manually specify it again unless the path in config.yaml is incorrect, in which case the correct path must be manually specified here.
|
||||
- `frontend_conf.cmvn_file`：The CMVN (Cepstral Mean and Variance Normalization) file used when extracting fbank features from WAV files, which is usually specified in config.yaml. There is no need to manually specify it again unless the path in config.yaml is incorrect, in which case the correct path must be manually specified here.
|
||||
|
||||
Other parameters are the same as mentioned above. A complete [example](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/infer_from_local.sh) can be found here.
|
||||
|
||||
<a name="Export"></a>
|
||||
## Export ONNX
|
||||
|
||||
### Command-line usage
|
||||
```shell
|
||||
funasr-export ++model=paraformer ++quantize=false ++device=cpu
|
||||
```
|
||||
|
||||
### Python
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="paraformer", device="cpu")
|
||||
|
||||
res = model.export(quantize=False)
|
||||
```
|
||||
|
||||
### Test ONNX
|
||||
```python
|
||||
# pip3 install -U funasr-onnx
|
||||
from funasr_onnx import Paraformer
|
||||
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
|
||||
model = Paraformer(model_dir, batch_size=1, quantize=True)
|
||||
|
||||
wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
|
||||
|
||||
result = model(wav_path)
|
||||
print(result)
|
||||
```
|
||||
|
||||
More examples ref to [demo](https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/python/onnxruntime)
|
||||
@@ -0,0 +1,436 @@
|
||||
(简体中文|[English](./README.md))
|
||||
|
||||
FunASR开源了大量在工业数据上预训练模型，您可以在 [模型许可协议](https://github.com/alibaba-damo-academy/FunASR/blob/main/MODEL_LICENSE)下自由使用、复制、修改和分享FunASR模型，下面列举代表性的模型，更多模型请参考 [模型仓库](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo)。
|
||||
|
||||
<div align="center">
|
||||
<h4>
|
||||
<a href="#模型推理"> 模型推理 </a>
|
||||
｜<a href="#模型训练与测试"> 模型训练与测试 </a>
|
||||
｜<a href="#模型导出与测试"> 模型导出与测试 </a>
|
||||
</h4>
|
||||
</div>
|
||||
|
||||
<a name="模型推理"></a>
|
||||
## 模型推理
|
||||
|
||||
### 快速使用
|
||||
|
||||
命令行方式调用：
|
||||
```shell
|
||||
funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
|
||||
```
|
||||
|
||||
python代码调用（推荐）
|
||||
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="paraformer-zh")
|
||||
|
||||
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
|
||||
print(res)
|
||||
```
|
||||
|
||||
### 接口说明
|
||||
|
||||
#### AutoModel 定义
|
||||
```python
|
||||
model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch_size=[int], hub=[str], **kwargs)
|
||||
```
|
||||
- `model`(str): [模型仓库](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo) 中的模型名称，或本地磁盘中的模型路径
|
||||
- `device`(str): `cuda:0`（默认gpu0），使用 GPU 进行推理，指定。如果为`cpu`，则使用 CPU 进行推理
|
||||
- `ncpu`(int): `4` （默认），设置用于 CPU 内部操作并行性的线程数
|
||||
- `output_dir`(str): `None` （默认），如果设置，输出结果的输出路径
|
||||
- `batch_size`(int): `1` （默认），解码时的批处理，样本个数
|
||||
- `hub`(str)：`ms`（默认），从modelscope下载模型。如果为`hf`，从huggingface下载模型。
|
||||
- `**kwargs`(dict): 所有在`config.yaml`中参数，均可以直接在此处指定，例如，vad模型中最大切割长度 `max_single_segment_time=6000` （毫秒）。
|
||||
|
||||
#### AutoModel 推理
|
||||
```python
|
||||
res = model.generate(input=[str], output_dir=[str])
|
||||
```
|
||||
- `input`: 要解码的输入，可以是：
|
||||
- wav文件路径, 例如: asr_example.wav
|
||||
- pcm文件路径, 例如: asr_example.pcm，此时需要指定音频采样率fs（默认为16000）
|
||||
- 音频字节数流，例如：麦克风的字节数数据
|
||||
- wav.scp，kaldi 样式的 wav 列表 (`wav_id \t wav_path`), 例如:
|
||||
```text
|
||||
asr_example1 ./audios/asr_example1.wav
|
||||
asr_example2 ./audios/asr_example2.wav
|
||||
```
|
||||
在这种输入 `wav.scp` 的情况下，必须设置 `output_dir` 以保存输出结果
|
||||
- 音频采样点，例如：`audio, rate = soundfile.read("asr_example_zh.wav")`, 数据类型为 numpy.ndarray。支持batch输入，类型为list：
|
||||
```[audio_sample1, audio_sample2, ..., audio_sampleN]```
|
||||
- fbank输入，支持组batch。shape为[batch, frames, dim]，类型为torch.Tensor，例如
|
||||
- `output_dir`: None （默认），如果设置，输出结果的输出路径
|
||||
- `**kwargs`(dict): 与模型相关的推理参数，例如，`beam_size=10`，`decoding_ctc_weight=0.1`。
|
||||
|
||||
|
||||
### 更多用法介绍
|
||||
|
||||
|
||||
#### 非实时语音识别
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
# paraformer-zh is a multi-functional asr model
|
||||
# use vad, punc, spk or not as you need
|
||||
model = AutoModel(model="paraformer-zh",
|
||||
vad_model="fsmn-vad",
|
||||
vad_kwargs={"max_single_segment_time": 60000},
|
||||
punc_model="ct-punc",
|
||||
# spk_model="cam++"
|
||||
)
|
||||
wav_file = f"{model.model_path}/example/asr_example.wav"
|
||||
res = model.generate(input=wav_file, batch_size_s=300, batch_size_threshold_s=60, hotword='魔搭')
|
||||
print(res)
|
||||
```
|
||||
注意：
|
||||
- 通常模型输入限制时长30s以下，组合`vad_model`后，支持任意时长音频输入，不局限于paraformer模型，所有音频输入模型均可以。
|
||||
- `model`相关的参数可以直接在`AutoModel`定义中直接指定；与`vad_model`相关参数可以通过`vad_kwargs`来指定，类型为dict；类似的有`punc_kwargs`，`spk_kwargs`；
|
||||
- `max_single_segment_time`: 表示`vad_model`最大切割音频时长, 单位是毫秒ms.
|
||||
- `batch_size_s` 表示采用动态batch，batch中总音频时长，单位为秒s。
|
||||
- `batch_size_threshold_s`: 表示`vad_model`切割后音频片段时长超过 `batch_size_threshold_s`阈值时，将batch_size数设置为1, 单位为秒s.
|
||||
|
||||
建议：当您输入为长音频，遇到OOM问题时，因为显存占用与音频时长呈平方关系增加，分为3种情况：
|
||||
- a)推理起始阶段，显存主要取决于`batch_size_s`，适当减小该值，可以减少显存占用；
|
||||
- b)推理中间阶段，遇到VAD切割的长音频片段，总token数小于`batch_size_s`，仍然出现OOM，可以适当减小`batch_size_threshold_s`，超过阈值，强制batch为1;
|
||||
- c)推理快结束阶段，遇到VAD切割的长音频片段，总token数小于`batch_size_s`，且超过阈值`batch_size_threshold_s`，强制batch为1，仍然出现OOM，可以适当减小`max_single_segment_time`，使得VAD切割音频时长变短。
|
||||
|
||||
#### 实时语音识别
|
||||
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
|
||||
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
|
||||
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
|
||||
|
||||
model = AutoModel(model="paraformer-zh-streaming")
|
||||
|
||||
import soundfile
|
||||
import os
|
||||
|
||||
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
|
||||
speech, sample_rate = soundfile.read(wav_file)
|
||||
chunk_stride = chunk_size[1] * 960 # 600ms
|
||||
|
||||
cache = {}
|
||||
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
|
||||
for i in range(total_chunk_num):
|
||||
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
|
||||
is_final = i == total_chunk_num - 1
|
||||
res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
|
||||
print(res)
|
||||
```
|
||||
|
||||
注：`chunk_size`为流式延时配置，`[0,10,5]`表示上屏实时出字粒度为`10*60=600ms`，未来信息为`5*60=300ms`。每次推理输入为`600ms`（采样点数为`16000*0.6=960`），输出为对应文字，最后一个语音片段输入需要设置`is_final=True`来强制输出最后一个字。
|
||||
|
||||
#### 语音端点检测（非实时）
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="fsmn-vad")
|
||||
|
||||
wav_file = f"{model.model_path}/example/vad_example.wav"
|
||||
res = model.generate(input=wav_file)
|
||||
print(res)
|
||||
```
|
||||
注：VAD模型输出格式为：`[[beg1, end1], [beg2, end2], .., [begN, endN]]`，其中`begN/endN`表示第`N`个有效音频片段的起始点/结束点，
|
||||
单位为毫秒。
|
||||
|
||||
#### 语音端点检测（实时）
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
chunk_size = 200 # ms
|
||||
model = AutoModel(model="fsmn-vad")
|
||||
|
||||
import soundfile
|
||||
|
||||
wav_file = f"{model.model_path}/example/vad_example.wav"
|
||||
speech, sample_rate = soundfile.read(wav_file)
|
||||
chunk_stride = int(chunk_size * sample_rate / 1000)
|
||||
|
||||
cache = {}
|
||||
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
|
||||
for i in range(total_chunk_num):
|
||||
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
|
||||
is_final = i == total_chunk_num - 1
|
||||
res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
|
||||
if len(res[0]["value"]):
|
||||
print(res)
|
||||
```
|
||||
注：流式VAD模型输出格式为4种情况：
|
||||
- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`：同上离线VAD输出结果。
|
||||
- `[[beg, -1]]`：表示只检测到起始点。
|
||||
- `[[-1, end]]`：表示只检测到结束点。
|
||||
- `[]`：表示既没有检测到起始点，也没有检测到结束点
|
||||
输出结果单位为毫秒，从起始点开始的绝对时间。
|
||||
|
||||
#### 标点恢复
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="ct-punc")
|
||||
|
||||
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
|
||||
print(res)
|
||||
```
|
||||
|
||||
#### 时间戳预测
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="fa-zh")
|
||||
|
||||
wav_file = f"{model.model_path}/example/asr_example.wav"
|
||||
text_file = f"{model.model_path}/example/text.txt"
|
||||
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
|
||||
print(res)
|
||||
```
|
||||
更多（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）
|
||||
|
||||
<a name="核心功能"></a>
|
||||
## 模型训练与测试
|
||||
|
||||
### 快速开始
|
||||
|
||||
命令行执行（用于快速测试，不推荐）：
|
||||
```shell
|
||||
funasr-train ++model=paraformer-zh ++train_data_set_list=data/list/train.jsonl ++valid_data_set_list=data/list/val.jsonl ++output_dir="./outputs" &> log.txt &
|
||||
```
|
||||
|
||||
python代码执行（可以多机多卡，推荐）
|
||||
|
||||
```shell
|
||||
cd examples/industrial_data_pretraining/paraformer
|
||||
bash finetune.sh
|
||||
# "log_file: ./outputs/log.txt"
|
||||
```
|
||||
详细完整的脚本参考 [finetune.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/finetune.sh)
|
||||
|
||||
### 详细参数介绍
|
||||
|
||||
```shell
|
||||
funasr/bin/train.py \
|
||||
++model="${model_name_or_model_dir}" \
|
||||
++train_data_set_list="${train_data}" \
|
||||
++valid_data_set_list="${val_data}" \
|
||||
++dataset_conf.batch_size=20000 \
|
||||
++dataset_conf.batch_type="token" \
|
||||
++dataset_conf.num_workers=4 \
|
||||
++train_conf.max_epoch=50 \
|
||||
++train_conf.log_interval=1 \
|
||||
++train_conf.resume=false \
|
||||
++train_conf.validate_interval=2000 \
|
||||
++train_conf.save_checkpoint_interval=2000 \
|
||||
++train_conf.keep_nbest_models=20 \
|
||||
++train_conf.avg_nbest_model=10 \
|
||||
++optim_conf.lr=0.0002 \
|
||||
++output_dir="${output_dir}" &> ${log_file}
|
||||
```
|
||||
|
||||
- `model`（str）：模型名字（模型仓库中的ID），此时脚本会自动下载模型到本读；或者本地已经下载好的模型路径。
|
||||
- `train_data_set_list`（str）：训练数据路径，默认为jsonl格式，具体参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
|
||||
- `valid_data_set_list`（str）：验证数据路径，默认为jsonl格式，具体参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
|
||||
- `dataset_conf.batch_type`（str）：`example`（默认），batch的类型。`example`表示按照固定数目batch_size个样本组batch；`length` or `token` 表示动态组batch，batch总长度或者token数为batch_size。
|
||||
- `dataset_conf.batch_size`（int）：与 `batch_type` 搭配使用，当 `batch_type=example` 时，表示样本个数；当 `batch_type=length` 时，表示样本中长度，单位为fbank帧数（1帧10ms）或者文字token个数。
|
||||
- `train_conf.max_epoch`（int）：`100`（默认），训练总epoch数。
|
||||
- `train_conf.log_interval`（int）：`50`（默认），打印日志间隔step数。
|
||||
- `train_conf.resume`（int）：`True`（默认），是否开启断点重训。
|
||||
- `train_conf.validate_interval`（int）：`5000`（默认），训练中做验证测试的间隔step数。
|
||||
- `train_conf.save_checkpoint_interval`（int）：`5000`（默认），训练中模型保存间隔step数。
|
||||
- `train_conf.avg_keep_nbest_models_type`（str）：`acc`（默认），保留nbest的标准为acc（越大越好）。`loss`表示，保留nbest的标准为loss（越小越好）。
|
||||
- `train_conf.keep_nbest_models`（int）：`500`（默认），保留最大多少个模型参数，配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 保留最佳的n个模型，其他删除，节约存储空间。
|
||||
- `train_conf.avg_nbest_model`（int）：`10`（默认），保留最大多少个模型参数，配合 `avg_keep_nbest_models_type` 按照验证集 acc/loss 对最佳的n个模型平均。
|
||||
- `train_conf.accum_grad`（int）：`1`（默认），梯度累积功能。
|
||||
- `train_conf.grad_clip`（float）：`10.0`（默认），梯度截断功能。
|
||||
- `train_conf.use_fp16`（bool）：`False`（默认），开启fp16训练，加快训练速度。
|
||||
- `optim_conf.lr`（float）：学习率。
|
||||
- `output_dir`（str）：模型保存路径。
|
||||
- `**kwargs`(dict): 所有在`config.yaml`中参数，均可以直接在此处指定，例如，过滤20s以上长音频：`dataset_conf.max_token_length=2000`，单位为音频fbank帧数（1帧10ms）或者文字token个数。
|
||||
|
||||
#### 多gpu训练
|
||||
##### 单机多gpu训练
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 1 --nproc_per_node ${gpu_num} \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
--nnodes 表示参与的节点总数，--nproc_per_node 表示每个节点上运行的进程数
|
||||
|
||||
##### 多机多gpu训练
|
||||
|
||||
在主节点上，假设IP为192.168.1.1，端口为12345，使用的是2个GPU，则运行如下命令：
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 2 --node_rank 0 --nproc_per_node ${gpu_num} --master_addr 192.168.1.1 --master_port 12345 \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
在从节点上（假设IP为192.168.1.2），你需要确保MASTER_ADDR和MASTER_PORT环境变量与主节点设置的一致，并运行同样的命令：
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES="0,1"
|
||||
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
|
||||
torchrun --nnodes 2 --node_rank 1 --nproc_per_node ${gpu_num} --master_addr 192.168.1.1 --master_port 12345 \
|
||||
../../../funasr/bin/train.py ${train_args}
|
||||
```
|
||||
|
||||
--nnodes 表示参与的节点总数，--node_rank 表示当前节点id，--nproc_per_node 表示每个节点上运行的进程数（通常为gpu个数）
|
||||
|
||||
#### 准备数据
|
||||
|
||||
`jsonl`格式可以参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
|
||||
可以用指令 `scp2jsonl` 从wav.scp与text.txt生成。wav.scp与text.txt准备过程如下：
|
||||
|
||||
`train_text.txt`
|
||||
|
||||
左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应
|
||||
右边为音频文件标注文本，格式如下：
|
||||
|
||||
```bash
|
||||
ID0012W0013 当客户风险承受能力评估依据发生变化时
|
||||
ID0012W0014 所有只要处理 data 不管你是做 machine learning 做 deep learning
|
||||
ID0012W0015 he tried to think how it could be
|
||||
```
|
||||
|
||||
|
||||
`train_wav.scp`
|
||||
|
||||
左边为数据唯一ID，需与`train_text.txt`中的`ID`一一对应
|
||||
右边为音频文件的路径，格式如下
|
||||
|
||||
```bash
|
||||
BAC009S0764W0121 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav
|
||||
BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav
|
||||
ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
|
||||
```
|
||||
|
||||
`生成指令`
|
||||
|
||||
```shell
|
||||
# generate train.jsonl and val.jsonl from wav.scp and text.txt
|
||||
scp2jsonl \
|
||||
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
|
||||
++data_type_list='["source", "target"]' \
|
||||
++jsonl_file_out="../../../data/list/train.jsonl"
|
||||
```
|
||||
|
||||
（可选，非必需）如果需要从jsonl解析成wav.scp与text.txt，可以使用指令：
|
||||
|
||||
```shell
|
||||
# generate wav.scp and text.txt from train.jsonl and val.jsonl
|
||||
jsonl2scp \
|
||||
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
|
||||
++data_type_list='["source", "target"]' \
|
||||
++jsonl_file_in="../../../data/list/train.jsonl"
|
||||
```
|
||||
|
||||
#### 查看训练日志
|
||||
|
||||
##### 查看实验log
|
||||
```shell
|
||||
tail log.txt
|
||||
[2024-03-21 15:55:52,137][root][INFO] - train, rank: 3, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.327), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)], {'data_load': '0.000', 'forward_time': '0.315', 'backward_time': '0.555', 'optim_time': '0.076', 'total_time': '0.947'}, GPU, memory: usage: 3.830 GB, peak: 18.357 GB, cache: 20.910 GB, cache_peak: 20.910 GB
|
||||
[2024-03-21 15:55:52,139][root][INFO] - train, rank: 1, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.334), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.285), ('acc', 0.823), ('loss_pre', 0.046), ('loss', 0.331), ('batch_size', 36)], {'data_load': '0.000', 'forward_time': '0.334', 'backward_time': '0.536', 'optim_time': '0.077', 'total_time': '0.948'}, GPU, memory: usage: 3.943 GB, peak: 18.291 GB, cache: 19.619 GB, cache_peak: 19.619 GB
|
||||
```
|
||||
指标解释：
|
||||
- `rank`：表示gpu id。
|
||||
- `epoch`,`step`,`total step`：表示当前epoch，step，总step。
|
||||
- `loss_avg_rank`：表示当前step，所有gpu平均loss。
|
||||
- `loss/ppl/acc_avg_epoch`：表示当前epoch周期，截止当前step数时，总平均loss/ppl/acc。epoch结束时的最后一个step表示epoch总平均loss/ppl/acc，推荐使用acc指标。
|
||||
- `lr`：当前step的学习率。
|
||||
- `[('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)]`：表示当前gpu id的具体数据。
|
||||
- `total_time`：表示单个step总耗时。
|
||||
- `GPU, memory`：分别表示，模型使用/峰值显存，模型+缓存使用/峰值显存。
|
||||
|
||||
##### tensorboard可视化
|
||||
```bash
|
||||
tensorboard --logdir /xxxx/FunASR/examples/industrial_data_pretraining/paraformer/outputs/log/tensorboard
|
||||
```
|
||||
浏览器中打开：http://localhost:6006/
|
||||
|
||||
### 训练后模型测试
|
||||
|
||||
|
||||
#### 有configuration.json
|
||||
|
||||
假定，训练模型路径为：./model_dir，如果改目录下有生成configuration.json，只需要将 [上述模型推理方法](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/README_zh.md#%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86) 中模型名字修改为模型路径即可
|
||||
|
||||
例如：
|
||||
|
||||
从shell推理
|
||||
```shell
|
||||
python -m funasr.bin.inference ++model="./model_dir" ++input=="${input}" ++output_dir="${output_dir}"
|
||||
```
|
||||
从python推理
|
||||
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="./model_dir")
|
||||
|
||||
res = model.generate(input=wav_file)
|
||||
print(res)
|
||||
```
|
||||
|
||||
#### 无configuration.json时
|
||||
|
||||
如果模型路径中无configuration.json时，需要手动指定具体配置文件路径与模型路径
|
||||
|
||||
```shell
|
||||
python -m funasr.bin.inference \
|
||||
--config-path "${local_path}" \
|
||||
--config-name "${config}" \
|
||||
++init_param="${init_param}" \
|
||||
++tokenizer_conf.token_list="${tokens}" \
|
||||
++frontend_conf.cmvn_file="${cmvn_file}" \
|
||||
++input="${input}" \
|
||||
++output_dir="${output_dir}" \
|
||||
++device="${device}"
|
||||
```
|
||||
|
||||
参数介绍
|
||||
- `config-path`：为实验中保存的 `config.yaml`，可以从实验输出目录中查找。
|
||||
- `config-name`：配置文件名，一般为 `config.yaml`，支持yaml格式与json格式，例如 `config.json`
|
||||
- `init_param`：需要测试的模型参数，一般为`model.pt`，可以自己选择具体的模型文件
|
||||
- `tokenizer_conf.token_list`：词表文件路径，一般在 `config.yaml` 有指定，无需再手动指定，当 `config.yaml` 中路径不正确时，需要在此处手动指定。
|
||||
- `frontend_conf.cmvn_file`：wav提取fbank中用到的cmvn文件，一般在 `config.yaml` 有指定，无需再手动指定，当 `config.yaml` 中路径不正确时，需要在此处手动指定。
|
||||
|
||||
其他参数同上，完整 [示例](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/infer_from_local.sh)
|
||||
|
||||
|
||||
<a name="模型导出与测试"></a>
|
||||
## 模型导出与测试
|
||||
### 从命令行导出
|
||||
```shell
|
||||
funasr-export ++model=paraformer ++quantize=false
|
||||
```
|
||||
|
||||
### 从Python导出
|
||||
```python
|
||||
from funasr import AutoModel
|
||||
|
||||
model = AutoModel(model="paraformer")
|
||||
|
||||
res = model.export(quantize=False)
|
||||
```
|
||||
|
||||
### 测试ONNX
|
||||
```python
|
||||
# pip3 install -U funasr-onnx
|
||||
from funasr_onnx import Paraformer
|
||||
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
|
||||
model = Paraformer(model_dir, batch_size=1, quantize=True)
|
||||
|
||||
wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
|
||||
|
||||
result = model(wav_path)
|
||||
print(result)
|
||||
```
|
||||
|
||||
更多例子请参考 [样例](https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/python/onnxruntime)
|
||||
Reference in new issue
Block a user