Zen3 Audio
Collection
Speech recognition + text-to-speech. • 7 items • Updated
Zen3 TTS Custom Voice
Zen3 TTS variant for zero-shot voice cloning from a short reference sample, carrying speaker identity and prosody across long-form synthesis.
Derived by fine-tuning Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice (Alibaba Cloud, Apache-2.0).
- Architecture:
Qwen3TTSForConditionalGeneration(qwen3_tts) - Parameters: ~1.7B
- Base model:
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
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-CustomVoice.
Provenance
Fine-tuned from Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice (Apache-2.0). See NOTICE for full attribution.
- Downloads last month
- 41
Model tree for zenlm/zen3-tts-custom-voice
Base model
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice