Nemotron 3.5 ASR
An automatic speech recognition (ASR) model released by NVIDIA that supports multilingual recognition and uses an encoder-decoder architecture.
Timeline (last 90 days)
NVIDIA has published a complete pipeline for adapting Nemotron 3.5 ASR to Saudi Arabian dialects.
On the SADA corpus, after replay-mix fine-tuning with roughly 90% Saudi dialect plus 7% English, WER on Najdi and Hijazi dialects dropped from 55.05% to 29.96%.
Nemotron 3.5 ASR has a 24-layer encoder.
With about 134 hours of target speech, partial freezing costs 2.4 percentage points of performance compared with full fine-tuning.
All Facts (4)
NVIDIA has published a complete pipeline for adapting Nemotron 3.5 ASR to Saudi Arabian dialects.
50%UnverifiedOn the SADA corpus, after replay-mix fine-tuning with roughly 90% Saudi dialect plus 7% English, WER on Najdi and Hijazi dialects dropped from 55.05% to 29.96%.
50%UnverifiedNemotron 3.5 ASR has a 24-layer encoder.
50%UnverifiedWith about 134 hours of target speech, partial freezing costs 2.4 percentage points of performance compared with full fine-tuning.
50%