How Far Can Synthetic Data Take Thai OCR?
Synthetic-only training adapts PaddleOCR-VL into Wayu-Paxa-OCR-Zero, cutting Thai printed-page CER from 6.64% to 1.24% without real labels.
2 stories, newest first · one card per story
Synthetic-only training adapts PaddleOCR-VL into Wayu-Paxa-OCR-Zero, cutting Thai printed-page CER from 6.64% to 1.24% without real labels.
Researchers distill a compact 82M-parameter Thai TTS from synthetic OmniVoice data, enabling on-device fixed-voice synthesis without reference audio.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views