NetTalk (dictionary)
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
- Training data
- 5,000 tokens
- Epochs
- 55
"The connections in the network are specified by a total of 18629 weight parameters (including a variable threshold for each unit)"
"A subset of the 1000 most commonly occurring words was selected from this dictionary based on frequency counts in the Brown corpus"
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
- How it was established
- Operation counting
18629 params * 2 FLOP/param * (3 for forward + backward pass) * 55 epochs * 1000 words/epoch * 4.5 letters/word (estimated number of letters)
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
Background
NetTalk (dictionary) was published by Princeton University, in the country recorded as United States of America, during June 1987. The publishing organisation is categorised as academia.
It works in the domain of Speech, and is recorded as performing the task of 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
Training it took a computation budget of roughly 2.8 × 10¹⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 5,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: highly cited,Historical significance.
Answers
NetTalk (dictionary) — common questions
NetTalk (dictionary)— when was it released?
It 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.
NetTalk (dictionary)— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of speech synthesis. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
NetTalk (dictionary)— how much compute was used to train it?
Training consumed 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.
NetTalk (dictionary)— 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.
NetTalk (dictionary)— 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 (dictionary)— how many parameters does it have?
It has a parameter count of 18.6K. "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.
NetTalk (dictionary)— who created it?
It was published by Princeton University, based in United States of America, an organisation categorised as academia.
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.