nanoporetech / fast-ctc-decode
Blitzing Fast CTC Beam Search Decoder
☆182Updated 10 months ago
Alternatives and similar repositories for fast-ctc-decode:
Users that are interested in fast-ctc-decode are comparing it to the libraries listed below
- CUDA-Warp RNN-Transducer☆212Updated 2 years ago
- ☆14Updated last year
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆198Updated 2 years ago
- Auto Segmentation Criterion (ASG) implemented in pytorch☆51Updated 3 years ago
- PyTorch implementation of RNN-Transducer(RNN-T).☆75Updated 3 years ago
- Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"☆83Updated 2 years ago
- The People’s Speech Dataset☆102Updated last year
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆86Updated last month
- Primer on CTC implementation in pure Python PyTorch code☆103Updated 8 months ago
- [NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition☆250Updated 2 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆141Updated last year
- A fast parallel implementation of RNN Transducer.☆310Updated last year
- Segment an audio file and obtain utterance alignments. (Python package)☆334Updated 10 months ago
- Code for prefix beam search tutorial by @labodk☆185Updated 4 years ago
- Levenshtein edit-distance on PyTorch and CUDA☆94Updated 2 years ago
- ☆68Updated 3 years ago
- PyTorch Implementations for End-to-End Automatic Speech Recognition☆126Updated 5 years ago
- An implementation of RNN-Transducer loss in TF-2.0.☆45Updated 2 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- Example code for a neural transducer model.☆62Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆68Updated 4 years ago
- ☆75Updated 3 years ago
- Implementaion RNN tranceducer☆22Updated 5 years ago
- ☆273Updated 4 years ago
- Onnx wrapper for espnet infrernce model☆161Updated 5 months ago
- This repo is for the SPL paper "Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap"☆118Updated 2 years ago
- A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆200Updated 6 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago