Instructions to use committa/it_IT-serena-medium-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Piper
How to use committa/it_IT-serena-medium-checkpoint with Piper:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
committa commited on
Commit ·
4c29ddc
1
Parent(s): 485cb1d
serena checkpoint epoch 94 (medium, base per finetuning italiano)
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ Finetuning base checkpoint for Piper TTS (VITS), trained **from scratch** on Ita
|
|
| 18 |
|
| 19 |
- Model: piper (piper_train), quality **medium**, 22.05 kHz
|
| 20 |
- Base voice: **serena** — female, neutral Standard Italian (no regional accent), synthetic
|
| 21 |
-
- Training: **94 epochs** from scratch, batch 10,
|
| 22 |
- Dataset: [committa/serena-synthetic-it-27h](https://huggingface.co/datasets/committa/serena-synthetic-it-27h)
|
| 23 |
- File: `epoch=94-step=559930.ckpt` — **keep this filename**: tooling (e.g. the TextyMcSpeechy dojo) parses the `epoch=N-step=M` pattern to pick the highest checkpoint
|
| 24 |
|
|
|
|
| 18 |
|
| 19 |
- Model: piper (piper_train), quality **medium**, 22.05 kHz
|
| 20 |
- Base voice: **serena** — female, neutral Standard Italian (no regional accent), synthetic
|
| 21 |
+
- Training: **94 epochs** from scratch, batch 10, 29,470 clips (27 h)
|
| 22 |
- Dataset: [committa/serena-synthetic-it-27h](https://huggingface.co/datasets/committa/serena-synthetic-it-27h)
|
| 23 |
- File: `epoch=94-step=559930.ckpt` — **keep this filename**: tooling (e.g. the TextyMcSpeechy dojo) parses the `epoch=N-step=M` pattern to pick the highest checkpoint
|
| 24 |
|