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

x-square-robot
/
X2-ASR-4B-0812

Automatic Speech Recognition
Transformers
Safetensors
Chinese
English
voxtral_realtime
realtime
speech-recognition
streaming-asr
bilingual
Model card Files Files and versions
xet
Community
1

Instructions to use x-square-robot/X2-ASR-4B-0812 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use x-square-robot/X2-ASR-4B-0812 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="x-square-robot/X2-ASR-4B-0812")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("x-square-robot/X2-ASR-4B-0812")
    model = AutoModelForMultimodalLM.from_pretrained("x-square-robot/X2-ASR-4B-0812", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
X2-ASR-4B-0812
9.68 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Kaiqfu's picture
Kaiqfu
Update model card with bilingual streaming ASR results at τ=480/960/2400 ms
0526348 verified 6 days ago
  • .gitattributes
    1.57 kB
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • LICENSE
    11.4 kB
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • NOTICE
    464 Bytes
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • README.md
    8.09 kB
    Update model card with bilingual streaming ASR results at τ=480/960/2400 ms 6 days ago
  • config.json
    1.57 kB
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • generation_config.json
    191 Bytes
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • model.safetensors
    9.66 GB
    xet
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • params.json
    1.34 kB
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • processor_config.json
    384 Bytes
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago
  • tekken.json
    14.9 MB
    xet
    Release X2-ASR-4B-0812: Stage-1 bilingual streaming ASR weights and model card 6 days ago