Skip to content
ModelListedExternal
Download

Zen3 Asr 0.6B

Compact 0.6B Zen3 automatic speech recognition model, sized for edge devices and latency-sensitive transcription.

Sourcehuggingface.co/zenlm/zen3-asr-0.6B/tree/2447445eec4645faffa3928c8a55ba79bf8850ec
KindText modelBase modelQwen/Qwen3-ASR-0.6BVersionmodelBgrade

Model source

Kind
Text model
File size
1.75 GB
Base model
Qwen/Qwen3-ASR-0.6B
Version
vmodel
Updated
Sep 27, 2026
Downloads
15
Source
Hugging Face

Source description

Zen3 ASR 0.6B

Compact ~0.6B Zen3 automatic speech recognition model, sized for edge devices and latency-sensitive transcription.

Derived by fine-tuning Qwen/Qwen3-ASR-0.6B (Alibaba Cloud, Apache-2.0).

  • Architecture: Qwen3ASRForConditionalGeneration (qwen3_asr)
  • Parameters: ~0.6B
  • Base model: Qwen/Qwen3-ASR-0.6B

Weights

This repository contains the model weights: model.safetensors, config and tokenizer files.

The model uses the qwen3_asr 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-ASR-0.6B.

Provenance

Fine-tuned from Qwen/Qwen3-ASR-0.6B (Apache-2.0). See NOTICE for full attribution.

Sources

1 source
Hugging FacePrimaryVersion 2447445eec4645faffa3928c8a55ba79bf8850ec
huggingface.co/zenlm/zen3-asr-0.6B/tree/2447445eec4645faffa3928c8a55ba79bf8850ec

Verified Aug 30

Model artifacts

1 artifact

model.safetensors

safetensors · 1.75 GB · SHA-256 79d6cbd4c98c…23ea · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 30huggingface.co/zenlm/zen3-asr-0.6B

--- license: apache-2.0 library_name: transformers pipeline_tag: automatic-speech-recognition language: - en - zh base_model: - Qwen/Qwen3-ASR-0.6B base_model_relation: finetune tags: - zen3 - zen3-asr - zenlm - qwen3-asr - speech-recognition - edge - low-latency --- # Zen3 ASR 0.6B Compact ~0.6B Zen3 automatic speech recognition model, sized for edge devices and latency-sensitive transcription. Derived by fine-tuning [`Qwen/Qwen3-ASR-0.6B`](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) (Alibaba Cloud, Apache-2.0). - Architecture: `Qwen3ASRForConditionalGeneration` (`qwen3_asr`) - Parameters: ~0.6B - Base model: [`Qwen/Qwen3-ASR-0.6B`](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) ## Weights This repository contains the model weights: `model.safetensors`, config and tokenizer files. The model uses the `qwen3_asr` 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-ASR-0.6B`](https://huggingface.co/Qwen/Qwen3-ASR-0.6B). ## Provenance Fine-tuned from [`Qwen/Qwen3-ASR-0.6B`](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) (Apache-2.0). See `NOTICE` for full attribution.

NoteAug 30huggingface.co/zenlm/zen3-asr-0.6B

Source context: 15 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo zenlm/zen3-asr-0.6B