Nov 20 Yesterday 00:44 v2: fine-tune on pyopenjtalk-plus re-annotated data (step 114,000); 16-sentence eval normalized CER 1.6% -> 1.0%, UTMOS 3.73 Nov 19 2 days ago 08:47 Samples table: show sample 3's corrected score (0.0% after numeral normalization); keep the original 29.2% in the note and label the 4-sentence row's scoring method 08:37 Fix Evaluation intro: describe both the 4-sentence Whisper-small check and the 16-sentence large-v3 formal evaluation 07:35 Correct the s03 CER claim (scoring artifact) and add the formal 16-sentence evaluation Nov 18 3 days ago 22:08 tiny-voca-ja: Japanese TTS model (4.5M params, retrained from the tiny-voca recipe)