The PyTorch-based audio source separation toolkit for researchers

Unofficial PyTorch implementation of Google AI's VoiceFilter system

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

Deep Recurrent Neural Networks for Source Separation

An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.

A PyTorch implementation of DNN-based source separation.

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

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

An implementation of audio source separation tools.

Offline media processing utility powered by FFmpeg, local AI, and fast right-click workflows.

Ultimate Vocal Remover for Google Colab

Strip background music from YouTube videos

Adaptive and Focusing Neural Layers for Multi-Speaker Separation Problem

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

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

Real time multilingual face translator

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

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

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.

Real-time vocal/instrumental separation using MDX-NET and MelBand Roformer models