NetTalk (transcription)

Closed weights Princeton University 18.6K parameters June 1987

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
Princeton University
Organisation type
Academia
Country
United States of America
Published
6 June 1987
Authors
TJ Sejnowski, CR Rosenberg

What it does

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

Domain
Speech
Task
Speech synthesis

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
18.6K

"The connections in the network are specified by a total of 18629 weight parameters (including a variable threshold for each unit)"

Training data
5,120 tokens

We used the first two pages of transcriptions, which contained 1024 words from a child in firstgrade

Epochs
55

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
2.8 × 10¹⁰ FLOP

18629 params * 2 FLOP/param * (3 for forward + backward pass) * 55 epochs * 1024 words/epoch * 4.5 letters/word

How it was established
Operation counting

How it is classified

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

Frontier model
Yes
Why it is tracked
Highly cited,Historical significance
Record confidence
Confident
Citations
2,558

Sources

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

Reference
Parallel Networks that Learn to Pronounce English Text
Last updated
11 February 2026

What the numbers mean

About this model

NetTalk (transcription) was published by Princeton University, in United States of America, in June 1987. academia is the category the publisher falls under.

It works in Speech, and is recorded as doing speech synthesis.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

Producing it required around 2.8 × 10¹⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 5,120 tokens went into training it.

Its inclusion criterion is highly cited,Historical significance.

Answers

NetTalk (transcription) — common questions

01

Who created NetTalk (transcription)?

NetTalk (transcription) was published by Princeton University, based in United States of America, categorised as academia.

02

When was NetTalk (transcription) released?

NetTalk (transcription) was published in June 1987. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is NetTalk (transcription) used for?

NetTalk (transcription) works in Speech, and is recorded as handling speech synthesis. 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.

04

How much compute was used to train NetTalk (transcription)?

Around 2.8 × 10¹⁰ 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.

05

What GPU do I need to run NetTalk (transcription)?

None. NetTalk (transcription) 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 NetTalk (transcription) open source?

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

07

How many parameters does NetTalk (transcription) have?

NetTalk (transcription) has 18.6K parameters. "The connections in the network are specified by a total of 18629 weight parameters (including a variable threshold for each unit)". 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.

Source

Original publication

Record last updated 11 February 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.