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
Trelis 's Collections
Cascade
Trelis Duplex
Tiron — Meeting Transcription & Diarization
Tara — Hindi & Hinglish ASR
LibriTTS Tokens + Codecs
Trelis Medical Benchmarks
Piper TTS ONNX Models
Transcribe British and American English Spelling
ARC AGI Python Programs
Trelis TRM
Chat Fine-tuning Datasets
Function Calling v3

Trelis Duplex

updated about 7 hours ago

Duplex speech-to-speech: tokenized English speech datasets with separated speaker tracks, and the duplex-0 model.

Upvote
-

  • Trelis/duplex-pre-training-yodas3-mimi

    Viewer • Updated about 7 hours ago • 3.63k • 37 • 12

    Note Pre-training: 408 hours from YODAS3.


  • Trelis/duplex-pre-training-podcasts-mimi

    Viewer • Updated about 7 hours ago • 3.34k • 28 • 1

    Note Pre-training: 340 hours from podcasts.


  • Trelis/duplex-conversational-podcasts-mimi

    Viewer • Updated about 7 hours ago • 1.05k • 25

    Note Conversational: 156 hours of two-speaker podcast conversation with frequent turn-taking.

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs