SYLIN

VibeVoice-ASR

by Microsoft · Model · Voice & audio

Supports over 50 languages natively; finetuning code and vLLM inference are available

AccessOpen weightsNeeds~1.6 GBDownload1.6 GBSize7B parametersLicenseMIT

Evidence

  1. Jul 23
    VibeVoice-ASR-BitNet for CPU: heterogeneous quantization shrinks 4.62 GB to 1.58 GB, real-time (RTF < 1) on 3+ CPU threads without a GPU
  2. Mar 12
    Available to test in Azure AI Foundry Labs
  3. Jan 21
    Open-sourced 7B speech-to-text handling 60 minutes of audio in one pass, outputting speaker, timestamps and content with custom hotwords

Cost to run

Alternatives

More VibeVoice-ASR
Built on VibeVoice-ASR