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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Luigi
/
Qwen3-ASR-Micro

Automatic Speech Recognition
Transformers
ONNX
Safetensors
GGUF
Chinese
English
qwen3_asr
speech-llm
distillation
jetson
traditional-chinese
code-switching
Model card Files Files and versions
xet
Community

Instructions to use Luigi/Qwen3-ASR-Micro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Luigi/Qwen3-ASR-Micro with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="Luigi/Qwen3-ASR-Micro")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("Luigi/Qwen3-ASR-Micro")
    model = AutoModelForMultimodalLM.from_pretrained("Luigi/Qwen3-ASR-Micro")
  • Notebooks
  • Google Colab
  • Kaggle
Qwen3-ASR-Micro / scripts
44 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Luigi's picture
Luigi
Improve accuracy via stacked KD (logit-KL + hidden-state): zh-CER 0.0865 -> 0.0722
e9f20bd verified 1 day ago
  • convert_qwen3_asr_to_gguf.py
    18.8 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago
  • english_prep3.py
    1.36 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago
  • pilot_gather.py
    2.13 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago
  • remap_student_to_thinker.py
    2.65 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago
  • scale_corpus.py
    3.46 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago
  • train_03b_hskd.py
    5.31 kB
    Improve accuracy via stacked KD (logit-KL + hidden-state): zh-CER 0.0865 -> 0.0722 1 day ago
  • train_03b_kd.py
    5.05 kB
    Improve accuracy via stacked KD (logit-KL + hidden-state): zh-CER 0.0865 -> 0.0722 1 day ago
  • train_student_full.py
    5.23 kB
    Qwen3-ASR-0.3B: distilled zh-TW/en student + GGUF + reproduction scripts 2 days ago