Parakeet
Parakeet is a family of automatic speech recognition models released by NVIDIA that transcribe speech into text.
Parakeet is a family of automatic speech recognition (ASR) models that NVIDIA built with NeMo, its toolkit for speech AI development. The models have been released since 2024, and their weights can be downloaded and run on a local computer.
Speech recognition converts spoken audio into text and is used for meeting notes, subtitles and transcripts for video editing. Because output can include a timestamp for each word, it also helps locate specific points in a recording.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.