70 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python p... | 364K | |
| Deep learning software to decode EEG, ECG or MEG signals | 66K | |
| Collection of ML models and benchmarking tools | 26K | |
| Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch | 16K | |
| Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural netw... | 15K | |
| Easy to use audio stem separation with a UI, using various models from UVR train... | 12K | |
| Accurate and general beat tracker | 11K | |
| Inference-only Band-Split Roformer separation toolkit | 10K | |
| Implementation of rectified flow and some of its followup research / improvement... | 9K | |
| AbLang2: An antibody-specific language model focusing on NGL prediction. | 8K | |
| An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, ... | 8K | |
| Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch | 7K | |
| Implementation of Band Split Roformer, SOTA Attention network for music source s... | 7K | |
| Implementation of GateLoop Transformer in Pytorch and Jax | 6K | |
| LocoFormer - Generalist Locomotion via Long-Context Adaptation | 4K | |
| Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Image... | 4K | |
| Time-Series-Optimized Transformer for Observability | 4K | |
| Native Sparse Attention | 3K | |
| 3K | ||
| Implementation of the new SOTA for model based RL, from the paper "Improving Tra... | 3K | |
| Video Diffusion - Pytorch | 2K | |
| a Foundation Model for Univariate Time Series Forecasting | 2K | |
| Memory-Augmented Sequence Models in Pytorch | 2K | |
| A high quality multi-voice text-to-speech library | 2K | |
| Unofficial implementation of iTransformer - SOTA Time Series Forecasting using A... | 2K | |
| Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in... | 2K | |
| Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch | 2K | |
| Explorations into the recently proposed Taylor Series Linear Attention | 2K | |
| Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaA... | 2K | |
| Implementation of the Transformer variant proposed in "Transformer Quality in Li... | 2K | |
| Implementation of Infini-Transformer in Pytorch | 2K | |
| Unofficial PyTorch implementation of "Moises-Light: Resource-efficient Band-spli... | 2K | |
| Gaia2 - Pytorch | 2K | |
| VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration | 1K | |
| 1K | ||
| A Python CLI for Ruth NLP | 1K | |
| A multi-voice TTS system trained with an emphasis on quality | 1K | |
| Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning | 1K | |
| 930 | ||
| Remove background music from videos - for accessibility and personal use | 686 | |
| Inference-only Mel-Band Roformer vocal separation toolkit | 542 | |
| Implementation of the proposed DeepCrossAttention by Heddes et al at Google rese... | 533 | |
| A PyPI package containing Chainsaw and Merizo predict methods to find clusters i... | 475 | |
| ncRNABert: Deciphering the landscape of non-coding RNA using language model | 459 | |
| SpatialReasoners: A framework for training Spatial Reasoning Models in any domai... | 459 | |
| Causal Attention with Lookahead Keys | 406 | |
| Strassen Attention | 375 | |
| Remove background music from videos - for accessibility and personal use | 355 | |
| data parsing / loading facility for handy audio machine learning. powered by lmd... | 353 | |
| Modular toolkit for rapidly building and customizing transformer architectures. | 347 |
