Cohere's new AI model can transcribe your audio
NewsBytes | March 26, 2026 11:40 PM CST
Transcribe outperforms popular models on Hugging Face Open ASR leaderboard
Transcribe outperforms several popular models on the Hugging Face Open ASR leaderboard, achieving a 5.42 WER and a reported 61% average win rate in human evaluations and can process a massive 525 minutes of audio in just one minute.
While it still has some trouble with Portuguese, German, and Spanish, Cohere reports that human evaluators gave Transcribe a 61% average win rate over other models.
Cohere plans to roll it out across its enterprise platform North and make it available through APIs, so expect to see this tech pop up in more apps soon.
READ NEXT
-
UP Weather Alert, March 30: Thunderstorms in Noida and Agra, Heatwave in Prayagraj
-
Start the week with a film: In 'Moon', the singular power of a single actor
-
Nurse attempts self-immolation in Sagar, condition critical
-
Rain in parts of TN, temperature likely to dip: Weather department
-
Aruna Irani reveals her untold love story with 'Suhaag' director Kuku Kohli
