docs: clarify Zen fine-tune of Qwen3 audio base + honest base_model attribution

bece6a3 verified 2 months ago

1.45 kB

license: apache-2.0
library_name: transformers
pipeline_tag: text-to-speech
language:
  - en
  - zh
base_model:
  - Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
base_model_relation: finetune
tags:
  - zen3
  - zen3-tts
  - zenlm
  - qwen3-tts
  - speech-synthesis
  - voice-design
  - controllable
  - 12hz

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.