facebookresearch / flashy
Framework for writing deep learning training loops. Lightweight, and retaining full freedom to design as you see fits. It handles checkpointing, logging, distributed, compatibility with Dora, and more!
☆108Updated last year
Alternatives and similar repositories for flashy:
Users that are interested in flashy are comparing it to the libraries listed below
- Implementation of Perceiver AR, Deepmind's new long-context attention network based on Perceiver architecture, in Pytorch☆86Updated last year
- Implementation of DiffWave and SaShiMi audio generation models☆121Updated last year
- A home for audio ML in JAX. Has common features, learnable frontends, pretrained supervised and self-supervised models.☆66Updated 2 years ago
- My attempts at applying Soundstream design on learned tokenization of text and then applying hierarchical attention to text generation☆86Updated 5 months ago
- Implementation of a Light Recurrent Unit in Pytorch☆47Updated 5 months ago
- A collection of useful audio datasets and transforms for PyTorch.☆138Updated 2 years ago
- A toolbox that provides hackable building blocks for generic 1D/2D/3D UNets, in PyTorch.☆85Updated last year
- ☆64Updated 7 months ago
- Audiogen Codec☆131Updated 8 months ago
- SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model, Accepted to IEEE SLT 2022☆112Updated 2 years ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆95Updated 8 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆120Updated 8 months ago
- Dora is an experiment management framework. It expresses grid searches as pure python files as part of your repo. It identifies experimen…☆281Updated last year
- PyTorch wrappers for using your model in audacity!☆175Updated last year
- Official code for Wav2Seq☆96Updated 2 years ago
- A collection of pre-trained audio models, in PyTorch.☆113Updated 2 years ago
- GOMIN; Gaudio Open Mel-spectrogram Inversion Network☆110Updated last year
- ☆15Updated 2 years ago
- The demo page of UniAudio☆33Updated last year
- A novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently.☆196Updated last year
- Song Describer is a data collection platform for annotating music with textual descriptions.☆57Updated 4 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆103Updated 4 months ago
- ☆83Updated last year
- Trainer for audio-diffusion-pytorch☆129Updated 2 years ago
- Blazing fast data loading with HuggingFace Dataset and Ray Data☆16Updated last year
- ☆66Updated 3 weeks ago
- A repository for benchmarking neural vocoders by their quality and speed.☆209Updated last week
- Official Implementation of EnCLAP (ICASSP 2024)☆91Updated 10 months ago
- Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.☆35Updated 2 years ago
- Inspired by "Neural Networks Fail to Learn Periodic Functions and How to Fix It"☆65Updated 10 months ago