FastSpeech 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
- Zhejiang University (ZJU),Microsoft Research Asia
- Organisation type
- Academia,Industry
- Country
- China
- Published
- 8 August 2022
- Authors
- Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
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
- 27M
- Training data
- tokens
27M
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
- 2.3 × 10¹⁸ FLOP
- How it was established
- Hardware
125000000000000 FLOP / GPU / sec * 17.02 GPU-hours * 3600 sec / hour * 0.3 [assumed utilization] = 2.2977e+18 FLOP
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
- NVIDIA V100
- Chips used
- 1
- Chip-hours
- 17
- Power draw
- 330 W
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.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- Last updated
- 28 November 2025
What the numbers mean
About this model
FastSpeech 2 was published by Zhejiang University (ZJU),Microsoft Research Asia, in China, in August 2022. The organisation is categorised as academia,Industry.
It works in Speech, and is recorded as doing text-to-speech (TTS).
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 roughly 2.3 × 10¹⁸ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.
Answers
FastSpeech 2 — common questions
When was FastSpeech 2 released?
FastSpeech 2 was published in August 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is FastSpeech 2 used for?
FastSpeech 2 works in Speech, and is recorded as handling text-to-speech (TTS). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train FastSpeech 2?
Around 2.3 × 10¹⁸ FLOP, on NVIDIA V100. 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.
What GPU do I need to run FastSpeech 2?
None. FastSpeech 2 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.
Is FastSpeech 2 open source?
No. FastSpeech 2 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does FastSpeech 2 have?
FastSpeech 2 has 27M parameters. 27M. 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.
Who created FastSpeech 2?
FastSpeech 2 was published by Zhejiang University (ZJU),Microsoft Research Asia, based in China, categorised as academia,Industry.
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.