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

aufklarer
/
Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8

Automatic Speech Recognition
Core ML
nemotron
streaming
conformer
rnn-t
multilingual
Model card Files Files and versions
xet
Community
1
Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8
642 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
aufklarer's picture
aufklarer
Fix model card license metadata
447095f verified 13 days ago
  • decoder.mlmodelc
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago
  • encoder.mlmodelc
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago
  • joint.mlmodelc
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago
  • .gitattributes
    1.52 kB
    initial commit about 2 months ago
  • README.md
    5.65 kB
    Fix model card license metadata 13 days ago
  • config.json
    589 Bytes
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago
  • languages.json
    2.02 kB
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago
  • tokenizer.model
    407 kB
    xet
    Add SentencePiece tokenizer.model alongside vocab.json — required by speech-swift WordBoosting (greedy vocab-fallback diverges from real SPM Unigram on OOV brand/technical terms; shipping this file makes the boost path end-to-end engageable). about 1 month ago
  • vocab.json
    236 kB
    Upload Nemotron-3.5 ASR Streaming 0.6B variant about 2 months ago