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

  • Log In
  • Sign Up

Jacaranda-Health
/
ASR-STT-8bit

Automatic Speech Recognition
Transformers
Safetensors
English
Swahili
whisper
8-bit precision
bitsandbytes
Model card Files Files and versions
xet
Community

Instructions to use Jacaranda-Health/ASR-STT-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Jacaranda-Health/ASR-STT-8bit with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="Jacaranda-Health/ASR-STT-8bit")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
    
    processor = AutoProcessor.from_pretrained("Jacaranda-Health/ASR-STT-8bit")
    model = AutoModelForSpeechSeq2Seq.from_pretrained("Jacaranda-Health/ASR-STT-8bit")
  • Notebooks
  • Google Colab
  • Kaggle
ASR-STT-8bit
Ctrl+K
Ctrl+K
  • 2 contributors
History: 9 commits
eolang's picture
eolang
Update README.md
3d4d1a8 verified 9 months ago
  • .gitattributes
    1.52 kB
    initial commit 9 months ago
  • README.md
    1.89 kB
    Update README.md 9 months ago
  • added_tokens.json
    34.6 kB
    Add processor for 8-bit quantized model 9 months ago
  • config.json
    1.82 kB
    Add 8-bit quantized speech-to-text model 9 months ago
  • generation_config.json
    3.68 kB
    Add 8-bit quantized speech-to-text model 9 months ago
  • merges.txt
    494 kB
    Add processor for 8-bit quantized model 9 months ago
  • model.safetensors
    825 MB
    xet
    Add 8-bit quantized speech-to-text model 9 months ago
  • normalizer.json
    52.7 kB
    Add processor for 8-bit quantized model 9 months ago
  • preprocessor_config.json
    356 Bytes
    Add processor for 8-bit quantized model 9 months ago
  • special_tokens_map.json
    2.19 kB
    Add processor for 8-bit quantized model 9 months ago
  • tokenizer_config.json
    283 kB
    Add processor for 8-bit quantized model 9 months ago
  • vocab.json
    1.04 MB
    Add processor for 8-bit quantized model 9 months ago