Automatic Speech Recognition (ASR) system trained on CommonVoice (zh-TW) dataset with Kaldi toolkit.
Simply run sh
run.sh
to train and test the three models below:
- Monophone
- Triphone (1st pass): Delta + Delta-Delta
- Triphone (2nd pass): LDA + MLLT
scripts/prepare_data.py
: Preprocess CommonVoice (zh-TW) for usage of Kaldi.
scripts/prepare_data.ipynb
: Full details and explanations of the prepare_data.py
.
See requirements.txt
to check if any required package is not installed.