audio-separation 开源项目推荐（121 个）

asteroid-team /asteroid

面向研究人员的基于PyTorch的音频源分离工具包

maum-ai /voicefilter

Unofficial PyTorch implementation of Google AI's VoiceFilter system

kaituoxu /Conv-TasNet

A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

posenhuang /deeplearningsourceseparation

Deep Recurrent Neural Networks for Source Separation

JackismyShephard /ultimate-rvc

一款应用程序，用于使用基于检索的语音转换创建基于音频的内容，例如歌曲封面和语音。

tky823 /DNN-based_source_separation

A PyTorch implementation of DNN-based source separation.

aishoot /LSTM_PIT_Speech_Separation

Two-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.

kaituoxu /TasNet

A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.

Gaurox /FrameShift

由 FFmpeg、本地 AI 和快速的右键工作流驱动的离线媒体处理工具。

tky823 /audio_source_separation

An implementation of audio source separation tools.

Ignema /youtube-music-remover

从YouTube视频中剥离背景音乐

Eddycrack864 /Ultimate-Vocal-Remover-5.6-for-Google-Colab

Ultimate Vocal Remover for Google Colab

SonyResearch /mimo-audio-separation

Official PyTorch implementation for "Iterative Audio Separation with Mixture Consistency via MIMO Model Extension"

crlandsc /torch-log-wmse

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Totoketchup /Adaptive-MultiSpeaker-Separation

Adaptive and Focusing Neural Layers for Multi-Speaker Separation Problem

crlandsc /torch-l1-snr

Variations of L1 SNR Loss function for training audio source separation machine learning models

perso-ai /perso-dubbing-plugin

AI video auto-dubbing plugin for coding agents — translate & dub videos into multiple languages via the Perso Dubbing API. Works with Claude Code, Cursor, Codex & Antigravity.

developers-cosmos /Mimasa

Real time multilingual face translator

crlandsc /moises-light

Unofficial PyTorch implementation of "Moises-Light: Resource-efficient Band-split U-Net For Music Source Separation"

zingmars /vocal-music-separation

Software that performs the separation of vocals from music using neural networks (part of my Bachelor's thesis).