ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models

Faster Whisper transcription with CTranslate2

Streamlit component allowing to record audio from the user's microphone and/or perform speech to text easily

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation

Use the Asana API to export Asana tasks and comments to HTML

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

Developer friendly Natural Language Processing ✨

Box SDK for Python

A command line interface for interacting with the Box API.

Large, modern dataset for speech recognition

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

The code for the bark-voicecloning model. Training and inference.

🔊 Text-Prompted Generative Audio Model

A lightweight implementation of Beam Search for sequence models in PyTorch.

Unofficial implementation of miipher

De-essing software to reduce sibilance in speech

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 implementation of Performer, a linear attention-based transformer, in Pytorch

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

Library for Textless Spoken Language Processing

A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.

Contrastive Language-Audio Pretraining

Official Jax Implementation of MaskGIT

A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

FMA: A Dataset For Music Analysis

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.