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

rajb3
/
kea-b

Automatic Speech Recognition
NeMo
English
speech
audio
NeMo
parakeet
TDT
FastConformer
quantization
binary
1-bit
quantization-aware-training
knowledge-distillation
Eval Results (legacy)
Model card Files Files and versions
xet
Community
1

Instructions to use rajb3/kea-b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • NeMo

    How to use rajb3/kea-b with NeMo:

    import nemo.collections.asr as nemo_asr
    asr_model = nemo_asr.models.ASRModel.from_pretrained("rajb3/kea-b")
    
    transcriptions = asr_model.transcribe(["file.wav"])
  • Notebooks
  • Google Colab
  • Kaggle
kea-b / tokenizer
267 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
rajb3's picture
rajb3
Kea-B: 1-bit Parakeet-TDT-0.6B-v2 (MB1 final export)
5e7c298 verified 14 days ago
  • tokenizer.model
    251 kB
    xet
    Kea-B: 1-bit Parakeet-TDT-0.6B-v2 (MB1 final export) 14 days ago
  • tokenizer.vocab
    10.4 kB
    Kea-B: 1-bit Parakeet-TDT-0.6B-v2 (MB1 final export) 14 days ago
  • vocab.txt
    5.07 kB
    Kea-B: 1-bit Parakeet-TDT-0.6B-v2 (MB1 final export) 14 days ago