DBLSTM

Parameters

29.9M

Published

Dec 8, 2013

DBLSTM is an AI model developed by University of Toronto (Canada), first published in December 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 29,900,000 parameters. It was trained on roughly 5M datapoints.

The reference paper has 1,597 citations.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Speech
Task: Speech recognition (ASR)
Parameters: 29,900,000
Dataset size: 5M
Citations: 1,597