kate-egorova / ASR-hybrid-decoding
This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs. The output is a mix of in-vocabulary words and phoneme sequences. This decoding is suitable for systems with only a small dictionary available and for further recovery of OOV words.
☆11Updated 4 years ago
Related projects: ⓘ
- In this repository, I try to combine k2 with speechbrain to decode well and fastly.☆16Updated 2 years ago
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Updated 5 years ago
- A SPMI Lab toolkit for language models.☆11Updated 7 years ago
- A KALDI/C++ implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆14Updated 5 years ago
- A handy dataset of noises for ASR☆19Updated 5 years ago
- This repository contains the Kaldi LF-MMI implementation of the paper "Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for…☆8Updated 2 years ago