facebookresearch / gtnLinks
Automatic differentiation with weighted finite-state transducers.
☆455Updated 3 years ago
Alternatives and similar repositories for gtn
Users that are interested in gtn are comparing it to the libraries listed below
Sorting:
- Fast Block Sparse Matrices for Pytorch☆545Updated 4 years ago
- Haste: a fast, simple, and open RNN library☆330Updated last year
- [Prototype] Tools for the concurrent manipulation of variably sized Tensors.☆251Updated 2 years ago
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,113Updated 3 years ago
- FastFormers - highly efficient transformer models for NLU☆705Updated 2 months ago
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆198Updated 2 years ago
- Automatic differentiation with weighted finite-state transducers.☆123Updated 3 years ago
- A fast parallel implementation of RNN Transducer.☆310Updated last year
- PyTorch dataset extended with map, cache etc. (tensorflow.data like)☆329Updated 2 years ago
- Efficient, check-pointed data loading for deep learning with massive data sets.☆208Updated last year
- Slicing a PyTorch Tensor Into Parallel Shards☆299Updated 3 years ago
- Transformer training code for sequential tasks☆612Updated 3 years ago
- End-to-end ASR/LM implementation with PyTorch☆596Updated 3 years ago
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆340Updated 4 years ago
- PyTorch layer-by-layer model profiler☆607Updated 4 years ago
- CUDA-Warp RNN-Transducer☆212Updated 2 years ago
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight …☆235Updated 2 years ago
- Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"☆83Updated 2 years ago
- Efficient GPU kernels for block-sparse matrix multiplication and convolution☆1,040Updated last year
- Library for 8-bit optimizers and quantization routines.☆716Updated 2 years ago
- High performance model preprocessing library on PyTorch☆650Updated last year
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆322Updated 2 years ago
- PyTorch, TensorFlow, JAX and NumPy — all of them natively using the same code☆698Updated 2 years ago
- Understanding the Difficulty of Training Transformers☆329Updated 3 years ago
- Pytorch Lightning Distributed Accelerators using Ray☆210Updated last year
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,095Updated this week
- Long Range Arena for Benchmarking Efficient Transformers☆757Updated last year
- 🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆494Updated 3 years ago
- PyTorch functions and utilities to make your life easier☆195Updated 4 years ago
- Problem Agnostic Speech Encoder☆441Updated last year