sepformer wham enhancement

提供商speechbrain
分类speech-enhancement
许可证apache-2.0
下载量135
星标0

简介

SepFormer WHAM Enhancement 是一款由 SpeechBrain 团队开发的语音增强模型，专注于从嘈杂的背景中提取清晰的人声。它采用了先进的 SepFormer 架构，能够有效处理复杂的真实场景噪声（如 WHAM 数据集所涵盖的街道、咖啡馆环境），在降低底噪的同时最大限度地保留语音的自然度。对于需要处理录音素材、开发语音助手或优化会议记录的开发者来说，这是一个理想的预训练方案。该模型上手难度较低，可直接集成到 SpeechBrain 框架中，是目前语音分离与增强领域性能领先的开源选择。

核心亮点

  • 基于 SepFormer 架构，高效分离人声与背景噪声
  • 针对真实世界复杂噪声场景进行了专项优化
  • 集成于 SpeechBrain，开发者快速部署难度低
  • 采用 Apache-2.0 协议，支持商业化灵活应用

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("speechbrain/sepformer-wham-enhancement")
tokenizer = AutoTokenizer.from_pretrained("speechbrain/sepformer-wham-enhancement")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download speechbrain/sepformer-wham-enhancement

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download speechbrain/sepformer-wham-enhancement config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('speechbrain/sepformer-wham-enhancement')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/speechbrain/sepformer-wham-enhancement

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/speechbrain/sepformer-wham-enhancement

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('speechbrain/sepformer-wham-enhancement')
tokenizer = AutoTokenizer.from_pretrained('speechbrain/sepformer-wham-enhancement')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model speechbrain/sepformer-wham-enhancement

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model speechbrain/sepformer-wham-enhancement README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('speechbrain/sepformer-wham-enhancement')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/speechbrain/sepformer-wham-enhancement.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/speechbrain/sepformer-wham-enhancement.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'speechbrain/sepformer-wham-enhancement')

完整文档

来源: HuggingFace

---
language: "en"
thumbnail:
tags:

  • audio-to-audio

  • Speech Enhancement

  • WHAM!

  • SepFormer

  • Transformer

  • pytorch

  • speechbrain

license: "apache-2.0"
metrics:
  • SI-SNR

  • PESQ

---

<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
<br/><br/>

SepFormer trained on WHAM! for speech enhancement (8k sampling frequency)

This repository provides all the necessary tools to perform speech enhancement (denoising) with a SepFormer model, implemented with SpeechBrain, and pretrained on WHAM! dataset with 8k sampling frequency, which is basically a version of WSJ0-Mix dataset with environmental noise and reverberation in 8k. For a better experience we encourage you to learn more about SpeechBrain. The given model performance is 14.35 dB SI-SNR on the test set of WHAM! dataset.

| Release | Test-Set SI-SNR | Test-Set PESQ |
|:-------------:|:--------------:|:--------------:|
| 01-12-21 | 14.35 | 3.07 |

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

code
pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Perform speech enhancement on your own audio file

python
from speechbrain.inference.separation import SepformerSeparation as separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-wham-enhancement", savedir='pretrained_models/sepformer-wham-enhancement')


for custom file, change path

est_sources = model.separate_file(path='speechbrain/sepformer-wham-enhancement/example_wham.wav')

torchaudio.save("enhanced_wham.wav", est_sources[:, :, 0].detach().cpu(), 8000)

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

Training

The training script is currently being worked on an ongoing pull-request.

We will update the model card as soon as the PR is merged.

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

#### Referencing SpeechBrain

bibtex
@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

#### Referencing SepFormer

bibtex
@inproceedings{subakan2021attention,
      title={Attention is All You Need in Speech Separation}, 
      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
      year={2021},
      booktitle={ICASSP 2021}
}


@article{subakan2023exploring,
  author={Subakan, Cem and Ravanelli, Mirco and Cornell, Samuele and Grondin, François and Bronzi, Mirko},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Exploring Self-Attention Mechanisms for Speech Separation}, 
  year={2023},
  volume={31},
  pages={2169-2180},
}

About SpeechBrain

  • Website: https://speechbrain.github.io/
  • Code: https://github.com/speechbrain/speechbrain/
  • HuggingFace: https://huggingface.co/speechbrain/
查看官方来源