STT Conformer-Transducer XL is an AI model developed by NVIDIA (United States), first published in April 2022. It works in the speech domain, on tasks such as speech recognition (asr).
Epoch AI has no training-compute estimate for this model. The model has 600,000,000 parameters. It was trained on roughly 437.8M datapoints.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.