Text-to-Speech
Piper
Italian
tts
checkpoint
finetuning
committa commited on
Commit
4c29ddc
·
1 Parent(s): 485cb1d

serena checkpoint epoch 94 (medium, base per finetuning italiano)

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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, ~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
 
 
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