NETtalk reimplementation
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
- Oregon State University
- Organisation type
- Academia
- Country
- United States of America
- Published
- 1 June 1990
- Authors
- Thomas G. Dietterich, Hermann Hild, Ghulum Bakiri
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Text-to-speech (TTS)
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
- 27.5K
- Training data
- 7,242 tokens
- Epochs
- 30
203*120+120*26=27480 “203 input units, 120 hidden units, and 26 output units”
“This training set was further subdivided to extract smaller training sets of 1000, 800, 400, 200, 100, and 50 words“
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
- 3.6 × 10¹⁰ FLOP
- How it was established
- Operation counting
Updated FLOP estimate: 2*27480*3*1000*7.24*30=35811936000=3.6e10
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
- Historical significance,Training cost
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- A Comparative Study of ID3 and Backpropagation for English Text-to-speech Mapping
- Last updated
- 28 November 2025
What the numbers mean
What this model is
NETtalk reimplementation was published by Oregon State University, in the country recorded as United States of America, during June 1990. The publishing organisation is categorised as academia.
It works in the domain of Speech, and is recorded as performing the task of text-to-speech (TTS).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Producing it required arithmetic totalling around 3.6 × 10¹⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 7,242 tokens of text.
The reason it appears in this catalogue at all: historical significance,Training cost.
Answers
NETtalk reimplementation — common questions
NETtalk reimplementation— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
NETtalk reimplementation— how many parameters does it have?
It has a parameter count of 27.5K. 203*120+120*26=27480 “203 input units, 120 hidden units, and 26 output units”. 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.
NETtalk reimplementation— who created it?
It was published by Oregon State University, based in United States of America, an organisation categorised as academia.
NETtalk reimplementation— when was it released?
It was published in June 1990. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
NETtalk reimplementation— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of text-to-speech (TTS). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
NETtalk reimplementation— how much compute was used to train it?
Training consumed around 3.6 × 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.
NETtalk reimplementation— 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.
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.