Tag
NVIDIA releases Nemotron 3.5 ASR, a 600M parameter multilingual streaming speech recognition model supporting 40 language-locales with a Cache-Aware FastConformer-RNNT architecture for low-latency transcription. The model supports configurable chunk sizes and is ready for commercial use under the OpenMDW-1.1 license.
This paper presents Flavors of Moonshine, a suite of tiny specialized ASR models for edge devices. The authors show that monolingual models trained on a balanced mix of human-labeled, pseudo-labeled, and synthetic data outperform larger multilingual models like Whisper, achieving state-of-the-art error rates for small models and enabling on-device ASR for underrepresented languages.