Resources
audio-transformers-course
huggingface/audio-transformers-course
The Hugging Face Audio Transformers Course teaches how to apply Transformer models to speech recognition, audio classification and other audio processing tasks, with open-source lessons and notebooks.
Topics
Related projects
koel17.3kKoel is a self-hosted music streaming solution built on Laravel and Vue. It scans your personal library and serves it through a modern web player with playlists, podcasts and integrations.
MMAudio2.3kMMAudio is a CVPR 2025 model for high-quality video-to-audio synthesis, generating synchronized sound from video and text with released checkpoints and code.
audioplayers2.1kA Flutter plugin for playing multiple audio files simultaneously across Android, iOS, web, and desktop. It gives app developers playback controls, streaming events, and consistent audio support on every platform.
Lavalink1.9kA standalone audio-sending node built on Lavaplayer. It lets Discord bots and similar clients stream music, resolve tracks, control players, and expose a REST API.
descript-audio-codec1.9kDescript's neural audio codec model, released with weights plus training and inference scripts. It compresses 44.1 kHz audio at very low bitrates while preserving fidelity.
RAVE1.8kThe official implementation of RAVE, a realtime neural audio variational autoencoder. It includes training, export, and realtime inference tools for timbre transfer and music generation.