Saaras v1

Parameters

1.5B

Published

Aug 13, 2024

Saaras v1 is an AI model developed by Sarvam (India), first published in August 2024. It works in the speech domain, on tasks such as speech recognition (asr) and speech-to-text.

Epoch AI has no training-compute estimate for this model. The model has 1,500,000,000 parameters.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Sarvam
Country of organization: India
Domain: Speech
Task: Speech recognition (ASR), Speech-to-text
Parameters: 1,500,000,000
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident