DistBelief Speech

Closed weights Google 47.2M parameters December 2012

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Google
Organisation type
Industry
Country
United States of America
Published
3 December 2012
Authors
J. Dean, G. Corrado, R. Monga, Kai Chen, M. Devin, Quoc V. Le, Mark Z. Mao, Marc'Aurelio Ranzato, A. Senior, P. Tucker, Ke Yang, A. Ng

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Speech recognition (ASR)

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
47.2M

"We used a deep network with five layers: four hidden layer with sigmoidal activations and 2560 nodes each, and a softmax output layer with 8192 nodes." "The network was fully-connected layer-to-layer, for a total of approximately 42 million model parameters." 2560*2560*4+2560*8192=47185920

Training data
1,100,000,000 tokens

"We trained on a data set of 1.1 billion weakly labeled examples"

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
3.1 × 10¹⁷ FLOP

https://www.wolframalpha.com/input?i=6+FLOP+*+47185920+*+1.1+billion Number of epochs unknown but most likely 1 and probably under 30. We could narrow down the uncertainty further if we knew something about the hardware.

How it was established
Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Wall-clock time
120 hours

Figure 4

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited
Record confidence
Speculative

Sources

Where this record came from and when it was last checked.

Reference
Large Scale Distributed Deep Networks
Last updated
28 November 2025

What the numbers mean

Background

DistBelief Speech was published by Google, in United States of America, in December 2012. The organisation is categorised as industry.

It works in Speech, and is recorded as doing speech recognition (ASR).

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

The training run consumed about 3.1 × 10¹⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 1,100,000,000 tokens of text.

Its inclusion criterion is highly cited.

Answers

DistBelief Speech — common questions

01

Is DistBelief Speech open source?

The licensing for DistBelief Speech was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does DistBelief Speech have?

DistBelief Speech has 47.2M parameters. "We used a deep network with five layers: four hidden layer with sigmoidal activations and 2560 nodes each, and a softmax output layer with 8192 nodes." "The network was fully-connected layer-to-layer, for a total of approximately 42 million model parameters." 2560*2560*4+2560*8192=47185920. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created DistBelief Speech?

DistBelief Speech was published by Google, based in United States of America, categorised as industry.

04

When was DistBelief Speech released?

DistBelief Speech was published in December 2012. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is DistBelief Speech used for?

DistBelief Speech works in Speech, and is recorded as handling speech recognition (ASR). A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

06

How much compute was used to train DistBelief Speech?

Around 3.1 × 10¹⁷ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

What GPU do I need to run DistBelief Speech?

None. DistBelief Speech is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.