Description
wav2vec 2.0 X-Large model checkpoint pre-trained on 158,000 hours and fine-tuned on 4,600 hours of Finnish speech.
| Koska saatavilla | 12 syysk. 2024 |
|---|---|
| Julkaisija | Zenodo |
Dataset Licences
- CC-BY-4.0
Tietoaineistot
-
Large-scale monolingual speech foundation models
Getman, Y. (Creator), GitHub, 24 elok. 2024
https://github.com/aalto-speech/large-scale-monolingual-speech-foundation-models
Tietoaineisto: Ohjelmisto tai koodi
Siteeraa tätä
- DataSetCite