arXiv cs.AI / cs.LG / cs.CL·11d agoRight Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM#babylm#cross-lingual#evaluationAI research
Hugging Face daily papers·24d agoHow Far Can Synthetic Data Take Thai OCR?#document-ai#low-resource#ocr
Hugging Face daily papers·24d agoBuilding and Evaluating Fixed-Voice Thai TTS from Synthetic Speech#distillation#low-resource#speech-synthesis
