kaldi-asr/kaldi is the official location of the Kaldi project.

chinese speech pretrained models

Bash scripts to upload files to google drive

Large, modern dataset for speech recognition

A 10000+ hours dataset for Chinese speech recognition

Phonetisaurus G2P

CMU Wilderness Multilingual Speech Dataset

A list of publically available audio data that anyone can download for ASR or other speech activities

xfspell — the Transformer Spell Checker

Multilingual Grapheme to Phoneme

Multilingual speech translation

scripts to align a given wave to its transcription using trained models by Kaldi

E2E-SincNet: Toward fully end-to-end speech recognition

A bunch of scripts exploiting several tools to perform inverse text normalization (ITN)

Code to train Automatic Speech-to-Text (AST) models