Science / Reel
Science · Video brief
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia unveils Nemotron 3.5 Transcribe, a cutting-edge transcription model supporting audio in up to 40 languages. It features speaker differentiation and extensive translation capabilities, although it only works with recorded audio.
Video won't play? Watch on YouTube →
Nvidia unveils Nemotron 3.5 Transcribe, a cutting-edge transcription model supporting audio in up to 40 languages. It features speaker differentiation and extensive translation capabilities, although it only works with recorded audio.
Full story and more reels: https://newsreel.video #Nvidia #VoiceAI #Transcription #TechNews #AI
Originally reported by TechCrunch.
Read the full story →
More in Science
Science
Scien
Science
A new wave of electric ferries is here in the US. Some even fly
Science
Scien
Science
Ukraine war briefing: Oleshky truce holding and demining under way to enable humanitarian corridor, Kyiv says
Science
Scien
Science
0 Comments
No comments yet. Be the first.