facebookresearch / gtn_applications
Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"
☆83Updated 2 years ago
Alternatives and similar repositories for gtn_applications:
Users that are interested in gtn_applications are comparing it to the libraries listed below
- Automatic differentiation with weighted finite-state transducers.☆122Updated 3 years ago
- Auto Segmentation Criterion (ASG) implemented in pytorch☆51Updated 3 years ago
- ☆48Updated 4 years ago
- Tensor2tensor experiment with SpecAugment☆46Updated 5 years ago
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆198Updated 2 years ago
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆68Updated 4 years ago
- Multistream CNN for Robust Acoustic Modeling☆40Updated 3 years ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆53Updated 2 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆141Updated last year
- Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)☆103Updated 2 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- ☆68Updated 3 years ago
- Fatcord's Alternative WaveRNN (Faster training)☆125Updated 6 years ago
- Example code for a neural transducer model.☆61Updated last year
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 2 years ago
- PyTorch Implementation of "Monotonic Chunkwise Attention" (ICLR 2018)☆80Updated 7 years ago
- ESPnet extensions for semi-supervised end-to-end speech recognition. See also https://github.com/ShigekiKarita/espnet-semi-supervised/tre…☆38Updated 5 years ago
- CMU multilingual speech repository☆31Updated 3 years ago
- ☆42Updated 6 years ago
- CUDA-Warp RNN-Transducer☆212Updated 2 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 5 years ago
- Implementation of "FastSpeech: Fast, Robust and Controllable Text to Speech"☆52Updated 5 years ago
- ESPnet-TTS Audio Sample HP☆21Updated 5 years ago
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆60Updated 2 years ago
- ☆12Updated 3 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆86Updated 2 months ago
- Recurrent Neural Aligner☆50Updated 5 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- ☆56Updated 2 years ago
- Bayesian spEEch Recognizer☆55Updated 4 years ago