Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Noblhyon
/
mini-omni2

Any-to-Any
Mini-Omni2
English
multimodal
speech-to-speech
vision-language
audio-processing
real-time
conversational-ai
qwen2
whisper
clip
Model card Files Files and versions
xet
Community
mini-omni2
3.68 GB
  • 1 contributor
History: 9 commits
Noblhyon's picture
Noblhyon
Add data folder with figures and demo
01c8fbf verified 29 days ago
  • data
    Add data folder with figures and demo 29 days ago
  • .gitattributes
    1.9 kB
    Add data folder with figures and demo 29 days ago
  • README.md
    6.58 kB
    Add comprehensive model card and documentation 29 days ago
  • ViT-B-32.pt
    354 MB
    xet
    Add ViT-B-32.pt: Vision Transformer weights for image encoding 29 days ago
  • lit_model.pth
    2.81 GB
    xet
    Add lit_model.pth: Main LitGPT model weights 29 days ago
  • model_config.yaml
    873 Bytes
    Add model_config.yaml: Model architecture and training configuration 29 days ago
  • small.pt
    484 MB
    xet
    Add small.pt: Compressed model checkpoint 29 days ago
  • tokenizer.json
    7.03 MB
    Add tokenizer.json: Tokenizer vocabulary and configuration 29 days ago
  • tokenizer_config.json
    1.29 kB
    Add tokenizer_config.json: Tokenizer configuration parameters 29 days ago