hainan-xv / PASM
Pronunciation-assisted Subword Modeling
☆29Updated 5 years ago
Related projects: ⓘ
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 2 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated last year
- ☆75Updated 2 years ago
- ☆31Updated 2 weeks ago
- CMU multilingual speech repository☆31Updated 2 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆37Updated 4 years ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆60Updated 6 months ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆47Updated 2 months ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- ☆16Updated 2 years ago
- it's ASR decoder and make graph project☆32Updated 2 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 3 years ago
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆31Updated 7 months ago
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 2 years ago
- A SPMI Lab toolkit for language models.☆11Updated 7 years ago
- Computes the MWER (minimum WER) Loss with beam search and negative sampling strategy.☆17Updated last year
- ☆22Updated 5 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆43Updated last year
- ☆64Updated 2 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- multilingual speech aligner☆70Updated 10 months ago
- Online streaming speaker change detection model in Pytorch☆34Updated last year
- Implementation of CTC alignment-based single step non-autoregressive transformer☆11Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆56Updated last year
- Multistream CNN for Robust Acoustic Modeling☆39Updated 3 years ago
- Properly handle position-dependent phones in a subword lexicon FST☆31Updated 3 years ago
- ☆16Updated 4 years ago
- HMM, CTC, RNN-Transducer, forward-backward algorithm☆19Updated last year
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆15Updated 3 years ago