Sarvam AI, in partnership with AI4Bharat, has launched Indic DiarBench, a benchmark dataset to assess ASR and speaker diarization across 22 scheduled Indian languages.
The dataset is available on Hugging Face
Aug 11, 2026
07:46 pm
What's the storySarvam AI has launched Indic DiarBench, an open benchmark dataset for automatic speech recognition (ASR) and speaker diarization across 22 Indian languages.
The dataset, which is available on Hugging Face, features around 108 hours of natural multi-speaker conversations.
Explained: Sarvam AI's Indic benchmark to test voice AI across 22 Indian languages - The Economic Times
First multilingual Indian speech recognition model trained on 65 languages and dialects released
IISc SPIRE Lab releases SraVaani speech AI model covering 65 Indian languages
Can Sarvam Be India's Full-Stack AI Company? Pratyush Kumar & Rajan Anandan
Building SpeakEasy AI: A Multilingual Voice Agent for Bharat
Building Dukaan Sathi: An AI Voice Assistant for India's Kirana Stores
Teaching AI to speak India
AI-powered live transmission, translation deployed in Delhi Assembly: Speaker - The Economic Times
How I Built Kisan Vaani: A Multi-Agent Voice AI Assistant for Indian Farmers
India has built a sovereign AI model. Almost everything underneath is rented
This launch addresses a major gap felt in the Indian AI ecosystem, especially voice models. AI voice tools have made rapid…
While speech technology for Indian languages has moved beyond the infancy stage, it still trails English and struggles with…
Indian startup Sarvam announced plans for a 1 trillion-parameter AI model, aiming to rival industry leaders OpenAI and Anthropic…
Bengaluru-based start-up Sarvam AI on Thursday launched Epoch Builder Edition, a developer and enterprise platform aimed at…
SraVaani, India's first multilingual speech recognition model, supports 65 languages, enhancing AI accessibility for underserved…
IISc's SPIRE Lab launches SraVaani, a speech AI model supporting 65 Indian languages, enhancing accessibility in voice technology.
