{"omc_version":"0.1","id":"speechbrain-asr-conformer-largescaleasr","name":"ASR Conformer Largescaleasr","provider":"SpeechBrain","released":"2025-02-06","licence":"Apache License 2.0","url":"https://huggingface.co/speechbrain/asr-conformer-largescaleasr","description":"ASR Conformer Largescaleasr is a compact English-only speech-to-text model from SpeechBrain that processes audio extremely fast on benchmark hardware. Its Apache licence and small footprint suit self-hosted deployment, though accuracy falls sharply on messy real-world recordings and no commercial hosts currently offer it.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":1.5},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":65,"of":74,"score":7.595714286,"higher_is_better":false,"variant":null}},"relationships":[],"card_meta":{"created":"2026-08-01T22:45:55.656Z","created_by":"LLMap pipeline","last_updated":"2026-08-03T20:17:39.922Z","source":"https://llmap.ai/models/speechbrain-asr-conformer-largescaleasr","omc_spec":"https://github.com/openmodelcard/spec"}}