Trained on CDLI's non-standard speech dataset (Kenyan English): cdli/kenyan_english_nonstandard_speech_v0.9
Performance on test set before and after:
- before: WER on test: 0.13
- after: WER on test: 0.09
More details: https://www.cdl-inclusion.com/ASRKenya
- Downloads last month
- 14
Model tree for cdli/whisper-large-v3_finetuned_kenyan_english_nonstandard_speech_v0.9
Base model
openai/whisper-small