ContextNet + Noisy Student

Closed weights Google January 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
19 January 2020
Authors
Daniel S. Park, Yu Zhang, Ye Jia, Wei Han, Chung-Cheng Chiu, Bo Li, Yonghui Wu, Quoc V. Le

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.

Training data
tokens

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
8.2 × 10²¹ FLOP

"We train 6 generations of models numbered 0 to 5, where we count the baseline model trained with the supervised set as the zeroth generation. Each generation is trained ... on 32 Google Cloud TPU chips for 10 days." The TPU version is likely v3 given this is a 2020 paper. we get 6 * 10 * 24 * 3600 * 32 * 123 tflops * 0.4 (assumed utilization) = 8.16e21

How it was established
Hardware

The training run

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

Training hardware
Google TPU v3
Wall-clock time
1,440 hours (60 days)

roughly 10 days

Compute cost
$14,226

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 are thus able to improve upon the previous state-of-the-art clean/noisy test WERs achieved on LibriSpeech 100h (4.74%/12.20%) and LibriSpeech (1.9%/4.1%)"

Record confidence
Confident
Citations
264

Sources

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

Reference
Improved Noisy Student Training for Automatic Speech Recognition
Last updated
25 May 2026

What the numbers mean

Background

ContextNet + Noisy Student was published by Google, in United States of America, in January 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.

How it was trained

The training run consumed about 8.2 × 10²¹ FLOP, on Google TPU v3. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Its inclusion criterion is sOTA improvement.

Answers

ContextNet + Noisy Student — common questions

01

Is ContextNet + Noisy Student open source?

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

02

How many parameters does ContextNet + Noisy Student have?

No parameter count has been published for ContextNet + Noisy Student, which is why no memory or speed figure appears on this page.

03

Who created ContextNet + Noisy Student?

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

04

When was ContextNet + Noisy Student released?

ContextNet + Noisy Student was published in January 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.

05

What is ContextNet + Noisy Student used for?

ContextNet + Noisy Student 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.

06

How much compute was used to train ContextNet + Noisy Student?

Around 8.2 × 10²¹ FLOP, on Google TPU v3. 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 ContextNet + Noisy Student?

None. ContextNet + Noisy Student 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 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.