Nvidia released Nemotron 3.5 Transcribe, a free 30-billion parameter open-weight model designed to transcribe and translate recorded audio across up to 40 languages.The model processes recordings up to an hour long, separates up to eight speakers, and runs on hardware ranging from edge chips like Jetson AGX Thor to Blackwell datacenter systems.Nvidia also released version 2 of its open-source speech dataset, Granary.https://en.hacks.gr/i-nvidia-paroysiase-neo-dorean-systima-technitis-noimosynis-poy-metatrepei-omilia-se-keimeno/#Nvidia #AI #MachineLearning #OpenSource
Nvidia released Nemotron 3.5 Transcribe, a free 30-billion parameter open-weight model designed to transcribe and transl...
