Whisper v2

Training compute

1.1×10²³ FLOP

Parameters

1.6B

Published

Dec 5, 2022

Whisper v2 is an AI model developed by OpenAI (United States), first published in December 2022. It works in the speech domain, on tasks such as speech recognition (asr).

Training it took an estimated 1.1×10²³ FLOP of compute (estimation method: comparison with other models). The model has 1,550,000,000 parameters. It was trained on roughly 12.4B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 7,066 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Speech
Task: Speech recognition (ASR)
Training compute: 1.1×10²³ FLOP
Compute estimation method: Comparison with other models
Parameters: 1,550,000,000
Dataset size: 12.4B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 7,066
Epoch confidence: Likely