{"omc_version":"0.1","id":"kyutai-stt-2-6b-en","name":"STT 2.6b en","provider":"Kyutai","released":"2025-06-06","licence":"Creative Commons Attribution 4.0","url":"https://huggingface.co/kyutai/stt-2.6b-en","description":"STT 2.6b en is a compact downloadable English speech-to-text model from Kyutai that processes audio extremely fast on benchmark hardware. Its accuracy is excellent for clean read-aloud recordings but drops sharply on accented speech or meetings, and it must be self-hosted as no providers currently offer it.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":3},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":36,"of":74,"score":5.741428571,"higher_is_better":false,"variant":null}},"relationships":[],"card_meta":{"created":"2026-08-01T22:45:47.855Z","created_by":"LLMap pipeline","last_updated":"2026-08-03T20:17:34.123Z","source":"https://llmap.ai/models/kyutai-stt-2-6b-en","omc_spec":"https://github.com/openmodelcard/spec"}}