rwth-i6 / returnnLinks
The RWTH extensible training framework for universal recurrent neural networks
☆372Updated last week
Alternatives and similar repositories for returnn
Users that are interested in returnn are comparing it to the libraries listed below
Sorting:
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆199Updated 3 years ago
- A fast parallel implementation of RNN Transducer.☆314Updated 2 years ago
- Python functions for reading kaldi data formats. Useful for rapid prototyping with python.☆378Updated 2 years ago
- End-to-End Attention-Based Large Vocabulary Speech Recognition☆265Updated 3 years ago
- experiments with RETURNN☆161Updated 3 months ago
- Code for end-to-end ASR with neural networks, build with TensorFlow☆110Updated 6 years ago
- End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)☆315Updated 7 years ago
- Speech recognition software where the neural net is trained with TensorFlow and GMM training and decoding is done in Kaldi☆173Updated 8 years ago
- ☆212Updated 7 years ago
- Small language toolkit for creation, interpolation and pruning of ARPA language models☆93Updated 3 years ago
- Yet another speech toolkit based on Kaldi and PyTorch☆173Updated 5 years ago
- The official repository of the Eesen project☆202Updated 9 years ago
- Code for prefix beam search tutorial by @labodk☆187Updated 5 years ago
- CMU Wilderness Multilingual Speech Dataset☆288Updated 6 years ago
- MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks☆139Updated 4 years ago
- Python wrappers for Kaldi data☆60Updated 8 years ago
- A listen attend and spell reimplementation in tensorflow, using a custom attention mechanism.☆44Updated 6 years ago
- Keras Interface for Kaldi ASR☆122Updated 8 years ago
- ASR with PyTorch☆140Updated 6 years ago
- Neural net code for lexicon-free speech recognition with connectionist temporal classification☆250Updated 9 years ago
- CUDA-Warp RNN-Transducer☆216Updated 2 years ago
- Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API …☆89Updated 6 years ago
- Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).☆130Updated 4 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆220Updated 4 years ago
- Implementation of all-neural speech recognition systems using Keras and Tensorflow☆145Updated 8 years ago
- The official repository of the Eesen project☆831Updated 6 years ago
- PyTorch code for end-to-end spoken language understanding (SLU) with ASR-based transfer learning☆230Updated 4 years ago
- A Pytorch Implementation of ClariNet☆292Updated 6 years ago
- A PyTorch Implementation of End-to-End Models for Speech-to-Text☆769Updated 2 years ago
- Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).☆284Updated 2 years ago