AINewsnow

NVIDIA's Nemotron 3.5 Transcribe Matches Top Speech AI With 6x Less Compute

This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.

NVIDIA's new 30B mixture-of-experts transcription model matches top open-weight accuracy at 2.8% WER while using 6x fewer active parameters than rivals.

Read the full story at AlphaSignal ↗

Timeline · 2 reports

  1. 2026-10-28 15:14 · AlphaSignal
    NVIDIA's Nemotron 3.5 Transcribe Tops Open Speech Leaderboard With 30B Model
  2. 2026-10-28 15:05 · AlphaSignal
    NVIDIA's Nemotron 3.5 Transcribe Matches Top Speech AI With 6x Less Compute

More stories

  1. NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt — Hugging Face Blog
  2. Voice AI in vogue: Nvidia releases new open transcription model — TechCrunch AI
  3. Memory-Enforced GPU Sharing in Kubernetes with NVIDIA CUDA 13.4 — NVIDIA Technical Blog
  4. 3 Ways to Boost MoE Inference on NVIDIA DGX Spark — NVIDIA Technical Blog
  5. NVIDIA RTX Spark Powers Neural Rendering and AI Characters in Games — NVIDIA Technical Blog
  6. Fine-Tuning NVIDIA Nemotron to Know Local Rules, Not Just Local Languages — NVIDIA Technical Blog
  7. Meta announces $95B offering to fund AI — Semafor Technology
  8. How NVIDIA Minerva Turns Telemetry Chaos Into Peak GPU Yield — NVIDIA Technical Blog

Get the daily brief of stories like this at 6:30 every morning →