TeaPoly / CTC-OptimizedLoss
Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
☆57Updated last year
Related projects ⓘ
Alternatives and complementary repositories for CTC-OptimizedLoss
- Memory efficient transducer loss computation☆68Updated 2 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆43Updated 2 years ago
- Implementaion RNN tranceducer☆21Updated 5 years ago
- ☆65Updated 2 years ago
- ☆75Updated 2 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆37Updated 4 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆20Updated 3 weeks ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- Code for reproducing experiments in "Domain-Adversarial Voice Activity Detection"☆23Updated 4 years ago
- Mining effective negative training samples for keyword spotting (PyTorch)☆57Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆139Updated last year
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆75Updated 3 years ago
- ☆41Updated last year
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated last year
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆31Updated 8 months ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆12Updated last year
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆46Updated 4 months ago
- ☆51Updated 3 years ago
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆67Updated 3 years ago
- it's a train acoustics model code lib☆26Updated 4 years ago
- [ICASSP2021] Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech…☆55Updated 4 years ago
- pytorch CTC implementation for ASR. Use eesen's fst decoder framework☆10Updated 4 years ago
- This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 20…☆46Updated 3 years ago
- Implements of CTC, Speech-Transformer and CIF for end-to-end speech recognition with pytorch☆21Updated 4 years ago
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆69Updated 2 years ago
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆38Updated last year