{"omc_version":"0.1","id":"microsoft-vibevoice-asr-hf","name":"VibeVoice ASR HF","provider":"Microsoft","released":"2026-03-02","licence":"MIT License","url":"https://huggingface.co/microsoft/VibeVoice-ASR-HF","description":"VibeVoice ASR HF is an 8-billion-parameter speech-to-text model from Microsoft with a permissive MIT licence. It turns audio into text across 51 claimed languages and is extremely fast on benchmark hardware, though its accuracy varies sharply with recording quality.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":2.5},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":49,"of":74,"score":6.288571429,"higher_is_better":false,"variant":null}},"relationships":[],"card_meta":{"created":"2026-08-01T22:45:48.236Z","created_by":"LLMap pipeline","last_updated":"2026-08-03T20:17:34.647Z","source":"https://llmap.ai/models/microsoft-vibevoice-asr-hf","omc_spec":"https://github.com/openmodelcard/spec"}}