nyra labs is the Vienna-based speech intelligence lab of nyra health. Its open model CrisperWhisper 2.0 transcribes speech exactly as it happens, capturing every word, pause, filler, repetition, and false start.
nyra labs: Nothing Is Noise nyra labs, the speech intelligence lab of nyra health based in Vienna, conducts research and builds open models designed to preserve and measure human speech. Its flagship release, CrisperWhisper 2.0, is a speech-to-text model that transcribes speech exactly as it happens, capturing every word, pause, filler, repetition, false start, and vocal sound. Key Features Verbatim Transcription: Captures spontaneous speech details, including fillers, repetitions, and cut-offs, across 10+ languages. Word-Level Timing: Word boundaries accurate to within 30 ms using guided cross-attention, with no separate aligner needed. Verbatimize Task: Converts existing spontaneous-speech corpora into faithful verbatim data while preserving trusted transcripts. Open and Production-Ready: Open weights and code on Hugging Face, with optimized inference, seamless longform support, and strong hallucination resistance. Industry-Leading Accuracy: Outperforms competitors in disfluency detection for both English and German.
Speech-to-Text
HQ COUNTRY
Vienna, Austria
Is this your company? To claim this listing or update its details, contact us at sunil@uniocommunity.com
