Multilingual DNN

Parameters

206.9M

Published

May 26, 2013

Multilingual DNN is an AI model developed by Google (United States), first published in May 2013. It works in the speech domain, on tasks such as speech recognition (asr).

Epoch AI has no training-compute estimate for this model. The model has 206,899,200 parameters. It was trained on roughly 3.1B datapoints.

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)
Parameters: 206,899,200
Dataset size: 3.1B
Training time: 672 h
Numerical format: FP32
Epoch confidence: Confident