Stars
Python module that identifies Chinese text as being Simplified or Traditional
Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)
Train your orthographic normalizer with the power of Fairseq
openvpi / DiffSinger
Forked from MoonInTheRiver/DiffSingerAn advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
MuseScore is an open source and free music notation software. For support, contribution, bug reports, visit MuseScore.org. Fork and make pull requests!
A morphological analyzer and spell checker for Kurdish in Hunspell
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Model parallel transformers in JAX and Haiku
Ongoing research training transformer models at scale
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
The simplest, fastest repository for training/finetuning medium-sized GPTs.