Thai Wav2Vec2.0 with CommonVoice V8
This addresses the problem of limited open-source Thai ASR models for individuals and the ASR community in Thailand, but it is incremental as it applies an existing method to new data.
The authors tackled the lack of robust open-source Thai automatic speech recognition (ASR) models by training a new model on a pre-trained XLSR-Wav2Vec with the Thai CommonVoice V8 corpus and a trigram language model, resulting in improved performance for Thai ASR.
Recently, Automatic Speech Recognition (ASR), a system that converts audio into text, has caught a lot of attention in the machine learning community. Thus, a lot of publicly available models were released in HuggingFace. However, most of these ASR models are available in English; only a minority of the models are available in Thai. Additionally, most of the Thai ASR models are closed-sourced, and the performance of existing open-sourced models lacks robustness. To address this problem, we train a new ASR model on a pre-trained XLSR-Wav2Vec model with the Thai CommonVoice corpus V8 and train a trigram language model to boost the performance of our ASR model. We hope that our models will be beneficial to individuals and the ASR community in Thailand.