x.comthread🚨 AI News | TestingCatalog (@testingcatalog) on X
Nemotron 3.5 Transcribe is an open-weight, promptable NVIDIA mixture-of-experts model with 30B total and about 4B active parameters. One checkpoint does transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding. The post says it ranked first in VoiceArena's comparison of 14 diarization plus ASR systems. The fetched text is cut off and gives no license or download details.
TL;DR Announces NVIDIA's open-weight 30B MoE speech model that handles 40-language transcription, diarization, translation and audio understanding.
Organisations named here
- NVIDIA
- VoiceArena
- TestingCatalog
- Nemotron
Technologies named here
- Nemotron 3.5 Transcribe
- Mixture of Experts
Techniques named here
- Mixture of experts
- Speaker diarization
- Contextual prompting
Related in models
