File size: 418 Bytes
b59c54a 748b954 |
1 2 3 4 5 6 7 8 9 |
---
language:
- no
- nb
---
Warmstarted from Chills model, then trained for 25 (de facto 50) epochs. Batch size 16, learning rate (√2)e-3 for the first 15(?) epochs and (5√2)e-4 for the last 10.
Dataset: [NST Norwegian Speech Synthesis](https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-15/) (CC0), shuffled together with a copy that has had all audio files under 6(?) seconds merged recursively. |