NetTalk (dictionary)

Training compute

2.8×10¹⁰ FLOP

Parameters

18.6K

Published

Jun 6, 1987

NetTalk (dictionary) is an AI model developed by Princeton University (United States), first published in June 1987. It works in the speech domain, on tasks such as speech synthesis. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 2.8×10¹⁰ FLOP of compute (estimation method: operation counting). The model has 18,629 parameters. It was trained on roughly 5K datapoints.

The reference paper has 2,558 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Princeton University
Country of organization: United States
Domain: Speech
Task: Speech synthesis
Training compute: 2.8×10¹⁰ FLOP
Compute estimation method: Operation counting
Parameters: 18,629
Dataset size: 5K
Citations: 2,558
Epoch confidence: Confident