zszheng147

BigVGAN

Official PyTorch implementation of BigVGAN (ICLR 2023)

torchtune

A Native-PyTorch Library for LLM Fine-tuning

CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

EmoBox

[INTERSPEECH 2024] EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark

fast_clip

open_clip

An open source implementation of CLIP.

OpenVoice

Instant voice cloning by MyShell.

flash-attention

Fast and memory-efficient exact attention

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

fish-speech

Brand new TTS solution

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

Spatial-AST

🦇 Encoder of BAT (Learning to Reason about Spatial Sounds with Large Language Models)

build-nanogpt

Video+code lecture on building nanoGPT from scratch

GigaSpeech2

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

ears_dataset

Expressive Anechoic Recordings of Speech (EARS)

AnimateDiff

Official implementation of AnimateDiff.

Omost

Your image is almost there!

tango

A family of diffusion models for text-to-audio generation.

ChatTTS

A generative speech model for daily dialogue.

icefall

x-transformers

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

vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

keops

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

SLAM-LLM

Speech, Language, Audio, Music Processing with Large Language Model

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

encodec

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

descript-audio-codec

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

apt-local-install

Tool for installing apt packages without root permission in user local space (aptli).

pykan

Kolmogorov Arnold Networks

stable-audio-tools

Generative models for conditional audio generation