TIGER DnR

提供商JusperLee
分类audio-to-audio
许可证apache-2.0
下载量107.5K
星标0

简介

TIGER DnR 是一款专注于音频去噪与修复（De-noising & Restoration）的音频到音频模型。它旨在解决录音环境嘈杂、底噪过大或音质受损等痛点，能够将受干扰的音频信号还原为纯净的人声或背景音。对于播客主、视频创作者或需要处理低质量录音的开发者来说，它提供了一种高效的自动化清理方案。该模型采用 Apache-2.0 开源协议，上手门槛较低，可作为音频预处理流水线中的关键环节，与常见的音频剪辑软件或语音识别（ASR）系统配合使用，显著提升后续处理的准确率。

核心亮点

  • 高效去除环境底噪，还原纯净音频信号
  • 适用于播客、采访等低质量录音的修复
  • Apache-2.0 协议，方便开发者集成部署
  • 可作为 ASR 预处理插件，提升语音识别率

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("JusperLee/TIGER-DnR")
tokenizer = AutoTokenizer.from_pretrained("JusperLee/TIGER-DnR")

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 JusperLee/TIGER-DnR

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 JusperLee/TIGER-DnR 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('JusperLee/TIGER-DnR')

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/JusperLee/TIGER-DnR

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/JusperLee/TIGER-DnR

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('JusperLee/TIGER-DnR')
tokenizer = AutoTokenizer.from_pretrained('JusperLee/TIGER-DnR')

完整文档

来源: HuggingFace

---
pipeline_tag: audio-to-audio
tags:

  • audio

license: apache-2.0
language:
  • en

---

<h3 align="center">Apollo: Band-sequence Modeling for High-Quality Audio Restoration</h3>
<p align="center">
<strong>Mohan Xu<sup>*</sup>, Kai Li<sup>*</sup>, Guo Chen, Xiaolin Hu</strong><br>
<strong>Tsinghua University, Beijing, China</strong><br>
<strong><sup>*</sup>Equal contribution</strong><br>
<a href="https://arxiv.org/abs/2410.01469">📜 ICLR 2025</a> | <a href="https://cslikai.cn/TIGER/">🎶 Demo</a> | <a href="https://huggingface.co/datasets/JusperLee/EchoSet">🤗 Dataset</a>

<p align="center">
<img src="https://visitor-badge.laobi.icu/badge?page_id=JusperLee.TIGER" alt="访客统计" />
<img src="https://img.shields.io/github/stars/JusperLee/TIGER?style=social" alt="GitHub stars" />
<img alt="Static Badge" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" />
</p>

<p align="center">

> TIGER is a lightweight model for speech separation which effectively extracts key acoustic features through frequency band-split, multi-scale and full-frequency-frame modeling.

💥 News

  • [2025-01-23] We release the code and pre-trained model of TIGER! 🚀
  • [2025-01-23] We release the TIGER model and the EchoSet dataset! 🚀

📜 Abstract

In this paper, we propose a speech separation model with significantly reduced parameter size and computational cost: Time-Frequency Interleaved Gain Extraction and Reconstruction Network (TIGER). TIGER leverages prior knowledge to divide frequency bands and applies compression on frequency information. We employ a multi-scale selective attention (MSA) module to extract contextual features, while introducing a full-frequency-frame attention (F^3A) module to capture both temporal and frequency contextual information. Additionally, to more realistically evaluate the performance of speech separation models in complex acoustic environments, we introduce a novel dataset called EchoSet. This dataset includes noise and more realistic reverberation (e.g., considering object occlusions and material properties), with speech from two speakers overlapping at random proportions. Experimental results demonstrated that TIGER significantly outperformed state-of-the-art (SOTA) model TF-GridNet on the EchoSet dataset in both inference speed and separation quality, while reducing the number of parameters by 94.3% and the MACs by 95.3%. These results indicate that by utilizing frequency band-split and interleaved modeling structures, TIGER achieves a substantial reduction in parameters and computational costs while maintaining high performance. Notably, TIGER is the first speech separation model with fewer than 1 million parameters that achieves performance close to the SOTA model.

🚀 Quick Start

Test with Pre-trained Model

bash
# Test using speech
python inference_speech.py --audio_path test/mix.wav

Test using DnR

python inference_dnr.py --audio_path test/test_mixture_466.wav

Train with EchoSet

bash
python audio_train.py --conf_dir configs/tiger.yml

Evaluate with EchoSet

bash
python audio_test.py --conf_dir configs/tiger.yml

📖 Citation

bibtex
@article{xu2024tiger,
  title={TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation},
  author={Xu, Mohan and Li, Kai and Chen, Guo and Hu, Xiaolin},
  journal={arXiv preprint arXiv:2410.01469},
  year={2024}
}

📧 Contact

If you have any questions, please feel free to contact us via [email protected].

查看官方来源