MMS-1B

Parameters

1B

Published

May 22, 2023

MMS-1B is an AI model developed by Meta AI (United States), first published in May 2023. 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 1,000,000,000 parameters. It was trained on roughly 13.6T datapoints. Training ran on 64 NVIDIA A100 SXM4 80 GB.

Access: Open weights (non-commercial). Its weights are openly available. The reference paper has 621 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Speech
Task: Speech recognition (ASR)
Parameters: 1,000,000,000
Dataset size: 13.6T
Training hardware: NVIDIA A100 SXM4 80 GB
Chips used: 64
Training power draw: 51.0 kW
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Citations: 621
Epoch confidence: Confident