Sarvam's new speech-to-text model beats Deepgram Nova-3 and GPT-4o Transcribe on noisy audio while covering all 22 Indian languages.
Full article content could not be extracted automatically. Read the original below.
Sarvam's Saaras V4 Brings All 22 Indian Languages Into One ASR Model
Sarvam's new speech-to-text model beats Deepgram Nova-3 and GPT-4o Transcribe on noisy audio while covering all 22 Indian languages.
Topics: