aalto-speech / subword-kaldi
Properly handle position-dependent phones in a subword lexicon FST
☆31Updated 4 years ago
Alternatives and similar repositories for subword-kaldi:
Users that are interested in subword-kaldi are comparing it to the libraries listed below
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- ☆27Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- ☆34Updated 5 months ago
- Phonetically-Oriented Word Error Rate☆33Updated 5 years ago
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 3 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 6 months ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 2 years ago
- Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model☆34Updated 5 years ago
- ☆16Updated 5 years ago
- CMU multilingual speech repository☆31Updated 2 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated 11 months ago
- Python wrapper for kaldi's arpa2fst☆38Updated 2 months ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆62Updated 11 months ago
- ☆48Updated 4 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 4 years ago
- ☆75Updated 2 years ago
- ☆68Updated 2 years ago
- Dataset of ICASSP 2021 MULTILINGUAL PHONETIC DATASET FOR LOW RESOURCE SPEECH RECOGNITION☆40Updated last year
- Multistream CNN for Robust Acoustic Modeling☆40Updated 3 years ago
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆16Updated 3 years ago
- python wrapper for kaldi's native I/O☆27Updated last month
- Articulatory features estimation using Listen Attend and Spell architecture.☆32Updated 4 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
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- ☆16Updated 2 years ago
- Simple Python package for fast DER computation☆32Updated last year
- Implementation of audio degradation processes☆101Updated 9 years ago
- ☆22Updated 7 years ago