NVIDIA releases 34B speech model with manifests covering 463,062 hours

NVIDIA released Nemotron 3.5 Transcribe, an open-weight 34B speech model that transcribes, translates, labels speakers and answers questions about recordings, alongside public manifests covering 463,062 hours of multilingual speech data, according to the October 28 announcement on Hugging Face. The release pairs the model with Granary v2, a data-curation pipeline and fine-tuning tools that let developers adapt speech recognition to their own terminology, accents and output formats locally. NVIDIA's announcement makes the hardware and benchmark caveats visible alongside the open weights.

NVIDIA releases 34B speech model with manifests covering 463,062 hours Nemotron 3.5 Transcribe combines transcription, translation, speaker labels and audio Q&A; Granary v2 adds public manifests and a reusable curation pipeline. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: Hugging Face Newsroom https://huggingface.co/blog/nvidia/nemotron-transcribe-granary Why it matters NVIDIA is pairing an open-weight speech model with reusable data and fine-tuning tools, giving developers a route to adapt transcription locally while making the hardware and benchmark caveats visible. NVIDIA released an open-weight speech model that can transcribe, translate, label speakers and answer questions about recordings, alongside public manifests for 463,062 hours of multilingual speech data. The October 28th announcement https://huggingface.co/blog/nvidia/nemotron-transcribe-granary?ref=runtimewire puts the model and its data-curation pipeline in developers' hands, with the promise that teams can tune speech recognition to their own terminology, accents and output formats.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.