Description
Scripts for training large-scale monolingual speech foundation models with 158K hours of Finnish speech
| Date made available | 24 Aug 2024 |
|---|---|
| Publisher | GitHub |
Dataset Licences
- Apache-2.0
Datasets
-
wav2vec 2.0 X-Large KAVI 150K h model checkpoint
Getman, Y. (Creator), Zenodo, 12 Sept 2024
DOI: 10.5281/zenodo.13754079, https://zenodo.org/records/13754080
Dataset
-
wav2vec 2.0 Large KAVI 150K h model checkpoint
Getman, Y. (Creator), Zenodo, 12 Sept 2024
DOI: 10.5281/zenodo.13754083, https://zenodo.org/records/13754084
Dataset
-
wav2vec 2.0 Base KAVI 150K h model checkpoint (fine-tuned)
Getman, Y. (Creator), Zenodo, 12 Sept 2024
DOI: 10.5281/zenodo.13754085, https://zenodo.org/records/13754086
Dataset