Update README.md
Browse filesremoved useless info
README.md
CHANGED
|
@@ -24,18 +24,6 @@ Custom Italian voice for [Piper](https://github.com/OHF-Voice/piper1-gpl), train
|
|
| 24 |
- Quality: medium
|
| 25 |
- Files: `it_IT-serena-medium.onnx` + `it_IT-serena-medium.onnx.json` (must stay together)
|
| 26 |
|
| 27 |
-
## v2 — fine-tuned
|
| 28 |
-
|
| 29 |
-
This release fixes a defect of the previous model: words at the start of a
|
| 30 |
-
sentence after `.?!` (e.g. "Purtroppo. **Domani** non posso.") were spoken
|
| 31 |
-
with a collapsed, almost inaudible duration.
|
| 32 |
-
|
| 33 |
-
Fix: fine-tuned from the v1 checkpoint on an extended dataset
|
| 34 |
-
(`serena-synthetic-it-28h`, +1,372 targeted sentence-initial phrases).
|
| 35 |
-
|
| 36 |
-
Inference defaults are unchanged (noise_scale 0.6 / noise_w 0.4), so existing
|
| 37 |
-
users get the fix without changing any setting.
|
| 38 |
-
|
| 39 |
## License
|
| 40 |
|
| 41 |
CC-BY-4.0 — this model is derived from
|
|
|
|
| 24 |
- Quality: medium
|
| 25 |
- Files: `it_IT-serena-medium.onnx` + `it_IT-serena-medium.onnx.json` (must stay together)
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## License
|
| 28 |
|
| 29 |
CC-BY-4.0 — this model is derived from
|