Moyu offline speech models

GGUF conversion of Qwen3-TTS 1.7B CustomVoice and its 12Hz tokenizer, Apache-2.0. The .chunkNNN files are 256 MiB slices consumed by Moyu's verified resumable downloader. F16 source revision: 0c0e3051f131929182e2c023b9537f8b1c68adfe. Tokenizer revision: 7dd38ad4e9bad454aae9cd937d0cd577604fe229. Q5_K is experimental. Model files are data, with no executable code. Full-file and chunk SHA-256 hashes are provided in catalog.json. Engine source: https://github.com/offgridai/qwen3-tts-cpp-streaming Moyu: https://github.com/InubashiriLix/moyu

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Inubashiri0817/moyu-voice

Base model

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Finetuned

(24)

this model