it_IT-serena-high-checkpoint

it_IT-serena — Piper training checkpoint (Italian, high)

Finetuning base checkpoint for Piper TTS (VITS), fine-tuned on Italian.

• Model: piper (piper_train), quality high, 22.05 kHz
• Base voice: serena — female, neutral Standard Italian (no regional accent), synthetic
• Training: 18 epochs of fine-tuning (resumed from the v1 checkpoint, 99 epochs from scratch) on committa/serena-synthetic-it-28h (30,842 clips, 28 h)
• Dataset: committa/serena-synthetic-it-28h
• File: epoch=18-step=105450.ckpt — piper_train convention: epoch=N-step=M, which tooling uses to pick the highest checkpoint
• Best validation: val_mel 0.3567 (epoch 18)

Why this checkpoint

Piper publishes no official pretrained checkpoint for Italian (the rhasspy/piper-checkpoints catalog has no it entry). This is the only public Italian high checkpoint that can be used as a finetuning base. It is the base used to build it_IT-serena-high, and it is fine-tuned on an extended dataset (serena-synthetic-it-28h) with targeted sentence-initial phrases for improved prosody at the start of sentences.

Sample

Audio of the base voice (it_IT-serena-high):

<audio controls src="https://huggingface.co/committa/it_IT-serena-high-checkpoint/resolve/main/samples/speaker_0.mp3"></audio>

Use as a base for finetuning other Italian voices

Any checkpoint of the same quality config (high) can be resumed with piper_train:

python -m piper_train \
    --dataset-dir /path/to/your_voice_training_folder \
    --resume_from_checkpoint epoch=18-step=105450.ckpt \
    --quality high

Because the base already speaks Italian (correct phonemes and prosody), a new Italian voice converges in far fewer epochs than from scratch — and with less data. This works for both female and male target voices: the timbre is learned from the new dataset, so with enough epochs the new voice fully takes over.

License

CC-BY-4.0 — derived from committa/serena-synthetic-it-28h. If you use this checkpoint to build a voice, credit the dataset and this model.