whisper-small-pld-hil
openai/whisper-small finetuned on
sapinsapin/pld.
Extended run: trained to convergence on the hil portion of PLD read speech, selected on held-out CER. WER/CER are lowercased on the held-out split; CER is the model-selection metric because Philippine-language orthography varies at the word level.
| metric | value |
|---|---|
| cer | 0.0712 |
| wer | 0.1094 |
Trained with finetune_asr.py from the
halohalo pipeline; the dataset
adapter normalizes each corpus to (audio@16k, text, speaker_id) so corpora
are swappable with a --dataset flag.