Modelpublic

zenlm/zen3-tts-voice-design

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes8downloads

Model Card

Zen3 TTS Voice Design

Zen3 TTS variant for voice design: synthesize new speakers from natural-language descriptors (timbre, age, accent, affect) without reference audio.

Derived by fine-tuning `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` (Alibaba Cloud, Apache-2.0).

—Architecture: Qwen3TTSForConditionalGeneration (qwen3_tts)
—Parameters: ~1.7B
—Base model: `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign`

Weights

This repository contains the model weights: model.safetensors (talker) plus a speech_tokenizer/ module (12 Hz codec), config and tokenizer files.

The model uses the qwen3_tts architecture and loads with transformers (>= 4.57). It is API-compatible with the upstream base — follow the inference recipe on the base model card `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign`.

Provenance

Fine-tuned from `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` (Apache-2.0). See NOTICE for full attribution.