DL scaling speech

Closed weights Baidu 193M parameters December 2017

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
Baidu
Organisation type
Industry
Country
China
Published
1 December 2017
Authors
Joel Hestness, Sharan Narang, Newsha Ardalani, G. Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, Yanqi Zhou

What it does

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

Domain
Speech
Task
Speech recognition (ASR)
Approach
Supervised

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
193M
Training data
2,149,200,000 tokens

8M utterances, 11940 hours, trained for up to 2048h Estimated number of words: 11940*120*60=85968000 Training size: 2048/11940=0.172 Training words: 85968000*0.172=14786496

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased

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
Training cost
Record confidence
Likely

Sources

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

Reference
Deep Learning Scaling is Predictable, Empirically
Last updated
28 November 2025

What the numbers mean

Where it came from

DL scaling speech was published by Baidu, in the country recorded as China, during December 2017. It comes out of an organisation categorised as industry.

It works in the domain of Speech, and is recorded as performing the task of speech recognition (ASR).

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

Training and provenance

Training consumed a corpus of around 2,149,200,000 tokens of text.

The reason it appears in this catalogue at all: training cost.

Answers

DL scaling speech — common questions

01

DL scaling speech— what is it used for?

It works in the domain of Speech, and is recorded as handling the task of 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.

02

DL scaling speech— what GPU do I need to run it?

None. This 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.

03

DL scaling speech— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

DL scaling speech— how many parameters does it have?

It has a parameter count of 193M. 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.

05

DL scaling speech— who created it?

It was published by Baidu, based in China, an organisation categorised as industry.

06

DL scaling speech— when was it released?

It was published in December 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.