Fused SwiGLU Triton kernels

SoftVC VITS Singing Voice Conversion

SoftVC VITS Singing Voice Conversion

[ECCV 2024] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

This project is dedicated to the implementation and research of Kolmogorov-Arnold convolutional networks. The repository includes implementations of 1D, 2D, and 3D convolutions with different kern…

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Tools for handling speech data in machine learning projects.

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

Sparsity-aware deep learning inference runtime for CPUs

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

A simple but complete full-attention transformer with a set of promising experimental features from various papers

A course in reinforcement learning in the wild

This repo provides the processed samples of the manuscript "MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-head Transformer with Convolution-augmented Jo…

An open source dataset for source separation

The PyTorch-based audio source separation toolkit for researchers

Conformer-based Metric GAN for speech enhancement

Deep Learning for Speech

✍️ A way to integrate LaTeX, VS Code, and Inkscape in macOS

ICASSP 2023-2024 Papers: A complete collection of influential and exciting research papers from the ICASSP 2023-24 conferences. Explore the latest advancements in acoustics, speech and signal proce…

An easy to use PyTorch to TensorRT converter

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.

Convmelspec: Convertible Melspectrograms via 1D Convolutions

Port of OpenAI's Whisper model in C/C++