chenjiasheng / mwer
mWER loss implementation in tensorflow
☆31Updated 4 years ago
Alternatives and similar repositories for mwer:
Users that are interested in mwer are comparing it to the libraries listed below
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 4 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- ☆75Updated 2 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- ☆48Updated 4 years ago
- it's a train acoustics model code lib☆26Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- ☆68Updated 2 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- it's ASR decoder and make graph project☆32Updated 2 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 3 months ago
- Conversion of recurrent neural network language models to weighted finite state transducers☆56Updated 6 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆76Updated 4 years ago
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆33Updated last year
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆68Updated 4 years ago
- ☆55Updated 4 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
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆21Updated 5 months ago
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Updated 6 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆141Updated last year
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- ☆41Updated 6 years ago
- ☆61Updated 2 years ago
- python codes to extract MFCC and FBANK speech features for Kaldi☆65Updated 6 years ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 2 years ago
- Audio LPC (linear prediction code) using mel spectorgram, compatible for LPCNet☆61Updated 3 years ago
- A PyTorch implementation of Speech Transformer with multi-GPUs, an End-to-End ASR with Transformer network on Mandarin Chinese. This code…☆10Updated 5 years ago