A Pytorch implementation of Speech Transformer, an End-to-End Automatic Speech Recognition with Transformer Network, Which directly converts acoustic features to character sequence using a signal neural network.
Tool to transform data from Nemo/Deepspeech format to Kaldi as described here — https://kaldi-asr.org/doc/data_prep.html
A Kaldi recipe for training a hybrid DNN-HMM speech recognition model
Transliteration pipeline for Kaldi-format ASR text: converts English and mixed-script tokens into native scripts with validation and error tracking.
A Speech to Text Personal Assist inspired by kaldi2 and joint-bert
Use kaldi pretrained nnet3 model to align individual sentences and get phone-level transcripts
ToDoList - Project of HIT Industry Intern and Practice
A minimal tool that helps transforming fixed grammars into compiled Finite State Transducers (FSTs). This thus makes them readable as language models (G.fst) in Kaldi.
Forced alignment toolkit for Nda’ Nda’, a Cameroonian language, for aligning audio recordings with transcriptions in language documentation and linguistic research.
BurrMill core
Resources for easily building ASR systems with Kaldi
Extract phone-level alignment and phonemic transcript from kaldi ali.*.gz files
To associate your repository with the kaldi topic, visit your repo's landing page and select "manage topics."