Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
Researchers distill a compact 82M-parameter Thai TTS from synthetic OmniVoice data, enabling on-device fixed-voice synthesis without reference audio.
The paper uses a large voice-cloning model (OmniVoice) as a synthetic data source to train Wayu-Paxa-TTS-Edge, an 82M-parameter fixed-voice Thai TTS student. The model achieves 68.2% Challenge-Set Keyword Accuracy (85.5% of Gemini 3.1), 91.4% pause precision, and CERs of 3.7% on Thai and 1.1% on English. It outperforms its teacher on pause placement and is open-sourced with its evaluation framework.
- 82M-parameter Wayu-Paxa-TTS-Edge trained entirely on synthetic speech
- Achieves 68.2% Challenge-Set Keyword Accuracy and 91.4% pause precision
- Outperforms OmniVoice teacher on pause placement; 3.7% Thai / 1.1% English CER
- Model and evaluation framework open-sourced
From the original article
1 min read at huggingface.co
In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice system that requires a speaker-specific corpus. We study a third route: using a large voice-cloning model as a programmable data source to turn a short voice reference (e. g.
By Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.