Modelpublic

sapinsapin/whisper-small-pld-bcl

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

0likes35downloads

Model Card

whisper-small-pld-bcl

`openai/whisper-small` finetuned on `sapinsapin/pld`.

Extended run: trained to convergence on the bcl 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	0.0400
wer	0.1115

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.