Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Qwen
/
Qwen3-Omni-30B-A3B-Captioner

Any-to-Any
Transformers
Safetensors
English
qwen3_omni_moe
text-to-audio
multimodal
Model card Files Files and versions
xet
Community
4

Instructions to use Qwen/Qwen3-Omni-30B-A3B-Captioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Qwen/Qwen3-Omni-30B-A3B-Captioner with Transformers:

    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Captioner")
    model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Captioner", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

I want to train a fine-timestamp-aligned True-Captioner

βž• 1
#4 opened 9 months ago by
mifanbushipeicai

Local Installation Video and Testing - Step by Step

πŸ‘ 1
#3 opened 10 months ago by
fahdmirzac

πŸ”₯πŸ”₯πŸ”₯桋评视钑

#2 opened 10 months ago by
leo009

Can this model perform ASR?

πŸ‘€ 2
3
#1 opened 11 months ago by
Jonathan0528
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs