NVIDIA open-sources Nemotron 3.5 Transcribe 30B ASR model; fine-tuning cuts word error rate 45.8%
NVIDIAAI · x · 2026-10-28
NVIDIA officially released Nemotron 3.5 Transcribe (30B-A4B), an open speech transcription model with weights, data, and recipes all available on Hugging Face, plus a live demo. It ships with Granary v2 open speech data and NeMo Speech fine-tuning tools; in a medical ASR case study, fine-tuning cut word error rate by 45.8% relative to the best prompt on held-out speakers, and NVIDIA published a guide for adapting it to your domain.
Related event: NVIDIA Open-Sources Nemotron 3.5 Transcribe 30B Speech Recognition Model(2 posts)→
More from Models
- Cryptographer points abliterated GLM at Telegram's secret-chat crypto — and it 'killed itself' — matthew_d_green · 2026-10-29
- Qoder offers DeepSeek-V4.1-Flash-1017 free through Oct 31 with zero credit cost — Aiden_Tech_Ai · 2026-10-29
- Top reasoning effort costs up to 42x more on tasks low effort already solves — zainhas · 2026-10-29
- RealityBench: 35 VLMs tested on physical work understanding, measuring stays a weak spot — arnabdotorg · 2026-10-28
- Permissive flagship open-model licenses fell from 75% to 35% in months — bookwormengr · 2026-10-28
- Anthropic Gets 80% of Revenue From API Pricing; DeepSeek Costs 20x Less — bindureddy · 2026-10-28