{"omc_version":"0.1","id":"abr-ai-niagara-84m-batch-en","name":"Niagara 84m Batch.en","provider":"Applied Brain Research","released":"2026-09-12","licence":{"tag":"Custom licence","state":"parsed","url":"https://llmap.ai/licenses/other"},"url":"https://huggingface.co/abr-ai/niagara-84m-batch.en","description":"Niagara 84m Batch.en is a speech-to-text model you can download and run yourself, built for bulk transcription where speed matters more than word accuracy. It is small enough for modest hardware, but on every kind of English audio we hold it transcribes worse than most of the field.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":2},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":66,"of":76,"score":7.4625,"higher_is_better":false,"variant":null}},"relationships":[{"type":"successor-of","id":"abr-ai-niagara-38m-batch-en"},{"type":"same-family","id":"abr-ai-niagara-9m-batch-en"},{"type":"same-family","id":"abr-ai-niagara-38m-batch-en"},{"type":"same-family","id":"abr-ai-niagara-19m-batch-en"}],"card_meta":{"created":"2026-09-28T20:18:02.401Z","created_by":"LLMap pipeline","last_updated":"2026-09-28T21:30:28.661Z","x_llmap_prices_checked":null,"x_llmap_prices_oldest":null,"x_llmap_prices_newest":null,"source":"https://llmap.ai/models/abr-ai-niagara-84m-batch-en","omc_spec":"https://github.com/openmodelcard/spec"}}