datasets: | |
- ArtFair/Voice-Data-New-Schema | |
metrics: | |
- wer | |
base_model: | |
- openai/whisper-large-v2 | |
Finetuned 1-epoch on the entire dataset (including all voices) |
datasets: | |
- ArtFair/Voice-Data-New-Schema | |
metrics: | |
- wer | |
base_model: | |
- openai/whisper-large-v2 | |
Finetuned 1-epoch on the entire dataset (including all voices) |