TIGER speech

提供商JusperLee
分类audio-to-audio
许可证apache-2.0
下载量14.3K
星标0

简介

TIGER speech 是一款基于 Apache-2.0 协议的开源语音到语音（Audio-to-Audio）模型。与传统的“语音转文字再转语音”的级联方案不同，它旨在实现更自然、低延迟的端到端语音交互，能更好地保留说话人的语气、情感和语调细节。对于开发者而言，该模型降低了构建高保真 AI 语音助手或实时翻译应用的门槛，适合需要极致自然听感且关注部署灵活性的项目场景，上手难度中等，可作为增强现有对话系统语音能力的底层组件。

核心亮点

  • 端到端语音处理，保留自然情感与语调
  • Apache-2.0 协议，企业级商用部署无压力
  • 低延迟响应，提升实时语音交互体验
  • 适用 AI 助手、实时翻译等高保真场景

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

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-speech

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-speech 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-speech')

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-speech

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-speech

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

完整文档

来源: HuggingFace

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

  • audio

license: apache-2.0
language:
  • en

---

<p align="center">
</p>
<h3 align="center">TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation</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.

TIGER

Overall pipeline of the model architecture of TIGER and its modules.

!TIGER Model Architecture

Results

Performance comparisons of TIGER and other existing separation models on *Libri2Mix, LRS2-2Mix, and EchoSet*. Bold indicates optimal performance, and italics indicate suboptimal performance.

!TIGER Model Architecture

Efficiency comparisons of TIGER and other models.

!TIGER Model Architecture

Comparison of performance and efficiency of cinematic sound separation models on DnR. '*' means the result comes from the original paper of DnR.

!TIGER Model Architecture

📦 Installation

bash
git clone https://github.com/JusperLee/TIGER.git
cd TIGER
pip install -r requirements.txt

🚀 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