>
NVIDIA NeMo, an end-to-end platform for the development of multimodal generative AI models at scale anywhere—on any cloud and on-premises—released the Parakeet family of automatic speech recognition (ASR) models. These state-of-the-art ASR models, developed in collaboration with Suno.ai, transcribe spoken English with exceptional accuracy.
Size Notes: "The model was trained on 64K hours of English speech collected and prepared by NVIDIA NeMo and Suno teams." "The NeMo toolkit [3] was used for training the models for over several hundred epochs."
Notes: 1.1B