Tacotron 2
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,University of California (UC) Berkeley
- Organisation type
- Industry,Academia
- Country
- United States of America
- Published
- 19 December 2017
- Authors
- Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu
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.
- Training data
- 2,125,888,704 tokens
"We train all models on an internal US English dataset[12], which contains 24.6 hours of speech from a single professional female speaker." 13,680 words/hour * 24.6 = 336528 words
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 3,047
Sources
Where this record came from and when it was last checked.
- Reference
- Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Prediction
- Last updated
- 25 May 2026
What the numbers mean
Background
Tacotron 2 was published by Google,University of California (UC) Berkeley, in the country recorded as United States of America, during December 2017. The publishing organisation is categorised as industry,Academia.
It works in the domain of Speech, and is recorded as performing the task of speech synthesis.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Training consumed a corpus of around 2,125,888,704 tokens of text.
Answers
Tacotron 2 — common questions
Tacotron 2— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Tacotron 2— who created it?
It was published by Google,University of California (UC) Berkeley, based in United States of America, an organisation categorised as industry,Academia.
Tacotron 2— when was it released?
It was published in December 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Tacotron 2— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of speech synthesis. These are the areas it was designed around; they describe intent rather than a hard boundary.
Tacotron 2— 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.
Tacotron 2— 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.
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.