ContextNet

Closed weights Google 112.7M parameters May 2020

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
7 May 2020
Authors
Wei Han, Zhengdong Zhang, Yu Zhang, Jiahui Yu, Chung-Cheng Chiu, James Qin, Anmol Gulati, Ruoming Pang, Yonghui Wu

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
112.7M

Table 5

Training data
349,200,000 tokens

970 hours of speech in the LibreSpeech experiments. There is mention of a "large scale experiment" which trained on audio from YouTube videos. Tracing the references, it appears to be similar to the dataset used in https://arxiv.org/abs/1610.09975, which has 125,000 hours of transcribed audio for training. However, they mention in footnote 2 that the training and evaluation set have changed from previous experiments. 125k hours at 13,680 words per hour = 1.71B words

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
Training code
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
SOTA improvement

"We demonstrate that on the widely used Librispeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the best previously published model of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters"

Record confidence
Likely
Citations
302

Sources

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

Reference
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Last updated
25 May 2026

What the numbers mean

What this model is

ContextNet was published by Google, in United States of America, in May 2020. 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.

What went into building it

The training set ran to roughly 349,200,000 tokens.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

ContextNet — common questions

01

How many parameters does ContextNet have?

ContextNet has 112.7M parameters. Table 5. 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.

02

Who created ContextNet?

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

03

When was ContextNet released?

ContextNet was published in May 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is ContextNet used for?

ContextNet works in Speech, and is recorded as handling speech recognition (ASR). These are the areas it was designed around; they describe intent rather than a hard boundary.

05

What GPU do I need to run ContextNet?

None. ContextNet 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.

06

Is ContextNet open source?

No. ContextNet has not had its weights published, so it exists only as a service controlled by its owner.

Source

Original publication

Record last updated 25 May 2026

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.