Stars
Test implementation of "Aligned Cross Entropy for Non-Autoregressive Machine Translation" https://arxiv.org/abs/2004.01655
A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.
Productive, portable, and performant GPU programming in Python.
MicroPython for K210 RISC-V, let's play with edge AI easier
Maix Speech AI lib, a fast and small speech lib running on embedded devices, including ASR, chat, TTS etc.
[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation
Speech-to-text server framework with next-gen Kaldi
Non-autoregressive Translation by Learning Target Categorical Codes
PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"
LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping
A torch implementation of a recursion which turns out to be useful for RNN-T.
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Memory efficient transducer loss computation
dqqcasia / st
Forked from bytedance/neurstEnd-to-end Speech Translation
Experiments to hack together a pyramidal bilstm from the listen, attend and spell paper
Google AI 2018 BERT pytorch implementation
Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)
An implementation of Jasper, QuartzNet, Citrinet and pipeline for training CTC-based ASR models