Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

qvac
/
TranscribePsy-250M-EU-sub

Automatic Speech Recognition
NeMo
Safetensors
asr
speech
multilingual
european-languages
on-device
edge
fastconformer
transducer
Model card Files Files and versions
xet
Community

Instructions to use qvac/TranscribePsy-250M-EU-sub with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • NeMo

    How to use qvac/TranscribePsy-250M-EU-sub with NeMo:

    import nemo.collections.asr as nemo_asr
    asr_model = nemo_asr.models.ASRModel.from_pretrained("qvac/TranscribePsy-250M-EU-sub")
    
    transcriptions = asr_model.transcribe(["file.wav"])
  • Notebooks
  • Google Colab
  • Kaggle
TranscribePsy-250M-EU-sub / assets
2.13 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
liu-tianchi's picture
liu-tianchi
Initial release
abc5c1f 16 days ago
  • blog
    Initial release 16 days ago
  • device_latency.png
    227 kB
    xet
    Initial release 16 days ago
  • wer_larger_models.png
    213 kB
    xet
    Initial release 16 days ago
  • wer_similar_size.png
    191 kB
    xet
    Initial release 16 days ago