ModelPrésentéExterne

Zen3 Tts 0.6B

Compact 0.6B Zen3 text-to-speech model at 12 Hz, sized for edge and latency-sensitive synthesis.

Sourcehuggingface.co/zenlm/zen3-tts-0.6B/tree/a81589481bea190e5ae1cd0f2db5fcd244fee022

TypeText modelModèle de baseQwen/Qwen3-TTS-12Hz-0.6B-BaseVersionBClasse

Source du modèle

Type: Text model
Taille du fichier: 1,70 GB
Modèle de base: Qwen/Qwen3-TTS-12Hz-0.6B-Base
Version: vmodel
Mis à jour: 26 oct. 2026
Téléchargements: 15
Source: Hugging Face

Description de la source

Zen3 TTS 0.6B

Compact ~0.6B Zen3 text-to-speech model at 12 Hz, sized for edge and latency-sensitive synthesis.

Derived by fine-tuning Qwen/Qwen3-TTS-12Hz-0.6B-Base (Alibaba Cloud, Apache-2.0).

Architecture: Qwen3TTSForConditionalGeneration (qwen3_tts)
Parameters: ~0.6B
Base model: Qwen/Qwen3-TTS-12Hz-0.6B-Base

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-0.6B-Base.

Provenance

Fine-tuned from Qwen/Qwen3-TTS-12Hz-0.6B-Base (Apache-2.0). See NOTICE for full attribution.

Sources

1 source

Hugging FacePrincipalVersion a81589481bea190e5ae1cd0f2db5fcd244fee022

huggingface.co/zenlm/zen3-tts-0.6B/tree/a81589481bea190e5ae1cd0f2db5fcd244fee022

Vérifié 26 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 1,70 GB · SHA-256 180b3b10eb1c…46f6 · Hugging Face

Download file

Extraits de sources

3 extraits

Readme7 aoûthuggingface.co/zenlm/zen3-tts-0.6B

--- license: apache-2.0 library_name: transformers pipeline_tag: text-to-speech language: - en - zh base_model: - Qwen/Qwen3-TTS-12Hz-0.6B-Base base_model_relation: finetune tags: - zen3 - zen3-tts - zenlm - qwen3-tts - speech-synthesis - edge - low-latency - 12hz --- # Zen3 TTS 0.6B Compact ~0.6B Zen3 text-to-speech model at 12 Hz, sized for edge and latency-sensitive synthesis. Derived by fine-tuning [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) (Alibaba Cloud, Apache-2.0). - Architecture: `Qwen3TTSForConditionalGeneration` (`qwen3_tts`) - Parameters: ~0.6B - Base model: [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) ## 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-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base). ## Provenance Fine-tuned from [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) (Apache-2.0). See `NOTICE` for full attribution.

Note26 oct.huggingface.co/zenlm/zen3-tts-0.6B

Source context: 15 downloads · 0 likes · Pipeline text-to-speech · Library transformers · Repo zenlm/zen3-tts-0.6B

Note7 aoûthuggingface.co/zenlm/zen3-tts-0.6B

Source context: 21 downloads · 0 likes · Pipeline text-to-speech · Library transformers · Repo zenlm/zen3-tts-0.6B