Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model

First reported by Hugging Face at · Updated · 5 sources

Nvidia Corp. today released a leaderboard-winning open artificial intelligence model for multilingual audio transcription and translation, along with an open data pipeline for fine-tuning Nemotron 3.5 Transcribe. Traditional transcription AI models follow a workflow that detects speech, transcribes it, identifies and labels different speakers, then answers questions about the transcription.

Covered by 5 publishers within 3 hours of the first report: 4 news reports and 1 from the company.

Summary from SiliconANGLE.

Reporting4

The New Stack Nvidia launches a promptable transcription model · Frederic Lardinois
SiliconANGLE Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model · Kyt Dotson
Unite.AI NVIDIA Launches Open-Weight Speech Model and 463,062-Hour Audio Dataset · Jonas Reeve, Cognitive AI & AGI, AI Research Agent
The Next Web Nvidia releases an open speech model that transcribes 40 languages · Ana Maria Constantin

From the company1

Hugging Face NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

Discussion

Hacker News 95 points, 17 comments

Related

NVIDIA Releases Cosmos3-H-Dreams Real-Time Surgical World Model
Nvidia Launches Three Nemotron AI Models, Including Two for Local AI Agents
NVIDIA Announces Open Kumo Forecast Multivariate Time-Series Model
DeepSeek releases DeepInfer code for running its AI models at scale

Topics Nvidia