lmnt-com / haste
Haste: a fast, simple, and open RNN library
☆329Updated last year
Alternatives and similar repositories for haste:
Users that are interested in haste are comparing it to the libraries listed below
- Automatic differentiation with weighted finite-state transducers.☆454Updated 3 years ago
- Fast Block Sparse Matrices for Pytorch☆546Updated 4 years ago
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight …☆235Updated last year
- Fast PyTorch based DSP for audio and 1D signals☆437Updated 2 weeks ago
- [Prototype] Tools for the concurrent manipulation of variably sized Tensors.☆253Updated 2 years ago
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆196Updated 2 years ago
- ☆153Updated 4 years ago
- PyTorch dataset extended with map, cache etc. (tensorflow.data like)☆328Updated 2 years ago
- Configuration classes enabling type-safe PyTorch configuration for Hydra apps☆209Updated 2 years ago
- Asynchronous Distributed Hyperparameter Optimization.☆291Updated last month
- Tensor Shape Annotation Library (numpy, tensorflow, pytorch, ...)☆264Updated 4 years ago
- Make TFRecord Usable Again☆87Updated last year
- PyTorch functions and utilities to make your life easier☆195Updated 3 years ago
- Automatic differentiation with weighted finite-state transducers.☆118Updated 2 years ago
- CUDA-Warp RNN-Transducer☆212Updated 2 years ago
- Configure Python functions explicitly and safely☆126Updated 3 months ago
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,110Updated 2 years ago
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆317Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- Pytorch Lightning Distributed Accelerators using Ray☆211Updated last year
- Shape and dimension inference (Keras-like) for PyTorch layers and neural networks☆571Updated 2 years ago
- Accelerate PyTorch models with ONNX Runtime☆358Updated last week
- Concise deep learning for JAX☆184Updated 4 years ago
- [ICLR'19] Trellis Networks for Sequence Modeling☆471Updated 5 years ago
- Block-sparse primitives for PyTorch☆153Updated 3 years ago
- Python implementation of GLN in different frameworks☆98Updated 4 years ago
- An ML framework to accelerate research and its path to production.☆265Updated 6 months ago
- Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"☆81Updated 2 years ago
- A fast parallel implementation of RNN Transducer.☆309Updated last year
- Fast Differentiable Sorting and Ranking☆587Updated last year