Universal-1 is our most powerful speech recognition model. Trained on over 12.5 million hours of multilingual audio data, Universal-1 achieves best-in-class speech-to-text accuracy across four major languages: English, Spanish, French, and German.
LeMUR is the easiest way to build LLM apps on spoken data - search, summarize, and ask questions, with knowledge of your spoken data.
We're introducing Conformer-2, our latest AI model for automatic speech recognition. Conformer-2 is trained on 1.1M hours of English audio data, extending Conformer-1 to provide improvements on proper nouns, alphanumerics, and robustness to noise.
LeMUR is our new framework for applying powerful LLMs to transcribed speech. With a single line of code, LeMUR can quickly process audio transcripts for up to 10 hours worth of audio content, which effectively translates into ~150k tokens, for tasks likes summarization and question answer.
We’ve trained a Conformer speech recognition model on 650K hours of audio data. The new model, Conformer-1, approaches human-level performance for speech recognition, reaching a new state-of-the-art on real-world audio data.
