DL scaling speech

Parameters

193M

Published

Dec 1, 2017

DL scaling speech is an AI model developed by Baidu (China), first published in December 2017. 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 193,000,000 parameters. It was trained on roughly 2.1B datapoints.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Baidu
Country of organization: China
Domain: Speech
Task: Speech recognition (ASR)
Parameters: 193,000,000
Dataset size: 2.1B
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Likely