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

gijs
/
voiceclap-transcriptions

Feature Extraction
OpenCLIP
audio
speech
clap
contrastive
transcription
wer
reference-free
voice
Model card Files Files and versions
xet
Community

Instructions to use gijs/voiceclap-transcriptions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • OpenCLIP

    How to use gijs/voiceclap-transcriptions with OpenCLIP:

    import open_clip
    
    model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:gijs/voiceclap-transcriptions')
    tokenizer = open_clip.get_tokenizer('hf-hub:gijs/voiceclap-transcriptions')
  • Notebooks
  • Google Colab
  • Kaggle
voiceclap-transcriptions
842 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
gijs's picture
gijs
VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin)
330ad80 verified 21 days ago
  • .gitattributes
    1.52 kB
    initial commit 21 days ago
  • README.md
    4.71 kB
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago
  • model.pt

    Detected Pickle imports (3)

    • "torch.FloatStorage",
    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    833 MB
    xet
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago
  • open_clip_model_config.json
    754 Bytes
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago
  • special_tokens_map.json
    239 Bytes
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago
  • tokenizer.json
    9.08 MB
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago
  • tokenizer_config.json
    526 Bytes
    VoiceCLAP-Transcriptions: multilingual reference-free WER substitute (10M + edit-distance ranking margin) 21 days ago