HF model

ayousanz / piper-plus-tsukuyomi-chan

A Japanese TTS model named tsukuyomi‑wavlm—fine‑tuned for 300 epochs on 100 utterances from the tsukuyomi corpus, using the WavLM discriminator and A1/A2/A3 prosody features on a VITS architecture, exported as a 61 MB ONNX file that generates 22.05 kHz syntheses.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
4,000
Hugging Face likes
12
Listed
Apr 6, 2026

Downloads (30-day window) over time

2k3k4kNovSepJulMayMarJan 20264,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 20262,000
May 20263,000
Jun 20262,000
Jul 20262,000
Aug 20264,000
Sep 20263,000
Oct 20264,000
Nov 20264,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Learn from slides & articles