NVIDIA Unveils AI Model Capable of Recognizing Speech in 40 Languages

NVIDIA has introduced Nemotron 3.5 Transcribe, an AI model designed for speech recognition, translation, and audio analysis. It supports 40 languages, including Turkish, and can process audio up to an hour long. The model can differentiate up to eight speakers in conversations and adapt to professional terminology.

Read the full article at Egemen Qazaqstan →

Headline and summary written by daryo. The full report belongs to Egemen Qazaqstan.