ContextNet + Noisy Student

Training compute

8.2×10²¹ FLOP

Published

Jan 19, 2020

ContextNet + Noisy Student is an AI model developed by Google (United States), first published in January 2020. It works in the speech domain, on tasks such as speech recognition (asr).

Training it took an estimated 8.2×10²¹ FLOP of compute (estimation method: hardware). Training ran on Google TPU v3 for about 1.4K hours. The compute alone is estimated at $14K in 2023 dollars.

Access: Unreleased. Its weights are not openly released. The reference paper has 264 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google
Country of organization: United States
Domain: Speech
Task: Speech recognition (ASR)
Training compute: 8.2×10²¹ FLOP
Compute estimation method: Hardware
Training hardware: Google TPU v3
Training time: 1,440 h
Training cost (2023 USD): $14K
Model accessibility: Unreleased
Open weights: No
Citations: 264
Epoch confidence: Confident