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
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | 2,000 |
| May 2026 | 3,000 |
| Jun 2026 | 2,000 |
| Jul 2026 | 2,000 |
| Aug 2026 | 4,000 |
| Sep 2026 | 3,000 |
| Oct 2026 | 4,000 |
| Nov 2026 | 4,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- Irodori-TTS-v4.1-Small-GGUFsakasegawa4kA speech.cpp‑only GGUF model for Japanese TTS that delivers single‑sentence audio in a reference voice or a described/auto‑chosen voice, using Euler sampling (default 40 steps) and supporting custom guidance, schedule, and speaker scaling.
- sarashina2.2-ttssbintuitions3kA Japanese‑centric, bilingual text‑to‑speech system built on a large language model that delivers highly accurate, natural, and stable pronunciation for both Japanese and English—including mixed code‑switching—and supports zero‑shot voice cloning across diverse speaking styles with responsibly sourced training data.
- irodori-tts-GGUFcstr1kIrodori‑TTS‑500M‑v3 is a 500 M‑parameter Rectified Flow Diffusion Transformer for Japanese/mixed text, released as GGUF/ggml quantised models (F16 ≈1.9 GB, Q4_K ≈852 MB, Q8_0 ≈896 MB) with an optional reference‑latent encoder and semantic DAC‑VAE decoder, licensed under MIT.
- Drama-3-JapaneseAratako1kJapanese fine‑tuned Fish Audio Drama 3 model enabling single‑speaker text‑to‑speech with optional reference audio, descriptive captions, and inline emotion tags for expressive delivery.
- Irodori-TTS-v4.1-Small-MF-CoreMLAILogDev1kA Core ML model and Swift SDK for Japanese TTS on iPhone/Apple‑Silicon Mac that supports full‑size and lightweight INT8 versions, voice cloning, text‑driven speaking style, offline synthesis to 48 kHz mono PCM16 WAV, with easy download, verification, and sample projects.
Resources in similar research fields
- LFM2.5-Audio-1.5B-JP-GGUFLiquidAI506kQuantized GGUF versions of LiquidAI’s LFM 2.5‑Audio 1.5B JP model, including language, audio encoder, and vocoder weights (F32/F16/Q8_0/Q4_0), plus CLI/Server runners for ASR and TTS with llama.cpp.Shared: Speech & Audio in NLP
voicevox_engineVOICEVOX1.8kVOICEVOX is a high-quality text-to-speech software that can be used for free.GitHubShared: Speech & Audio in NLP
voicevox_coreVOICEVOX1.2kThe core of VOICEVOX, a medium-quality text-to-speech software that can be used for free.GitHubShared: Speech & Audio in NLP
jpreprocessjpreprocess61Japanese text preprocessor for Text-to-Speech applications (OpenJTalk rewrite in rust language)GitHubShared: Speech & Audio in NLP- japanese-hubert-base-phoneme-ctcprj-beatrice4kFine‑tuned Japanese phoneme CTC model based on rinna/japanese‑hubert‑base, trained with ReazonSpeech v2 data and pyopenjtalk‑plus labels, achieving improved accuracy in a new v2 release (prj-beatrice/japanese-hubert-base-phoneme-ctc-v2).Shared: Speech & Audio in NLP
- japanese-hubert-base-phoneme-ctc-v3prj-beatrice2kFine‑tuned Japanese HuBERT‑base for CTC phoneme recognition (v3), adding MeCab N‑best with pyopenjtalk‑plus post‑processing, a weighted loss combining CTC and MeCab costs, updated exclusion rules, and a new “ty” phoneme.Shared: Speech & Audio in NLP