YaFSDP: Yet another Fully Sharded Data Parallel

Awesome speech/audio LLMs, representation learning, and codec models

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

Reference-aware automatic speech evaluation toolkit

A developer's guide to management: an open-sourced handbook for leading software engineering teams.

A Neural Framework for MT Evaluation

The strictest and most opinionated python linter ever!

dataset of podcasts and episodes

A Unified Library for Parameter-Efficient and Modular Transfer Learning

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

Versatile audio super resolution (any -> 48kHz) with AudioSR.

Machine Learning Engineering Open Book

Text-to-Audio/Music Generation

Voice Conversion With Just Nearest Neighbors

FTP client package for Go

A high-throughput and memory-efficient inference and serving engine for LLMs

Noise supression using deep filtering

A Very Low-Bitrate Codec for Speech Compression

Stable Diffusion inference benchmarks

A timeline of the latest AI models for audio generation, starting in 2023!

Download your Spotify playlists and songs along with album art and metadata (from YouTube if a match is found).

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

🔊 Text-Prompted Generative Audio Model

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Contrastive Language-Audio Pretraining

Audio Dataset for training CLAP and other models

An open-source efficient deep learning framework/compiler, written in python.

Official Pytorch Implementation of the paper: Wavelet Diffusion Models are fast and scalable Image Generators (CVPR'23)

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.