FastSpeech 2

Closed weights Zhejiang University (ZJU),Microsoft Research Asia 27M parameters August 2022

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

27M

Training data
tokens

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

125000000000000 FLOP / GPU / sec * 17.02 GPU-hours * 3600 sec / hour * 0.3 [assumed utilization] = 2.2977e+18 FLOP

How it was established
Hardware

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

01

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.

02

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.

03

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.

04

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.

05

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.

06

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.

07

Who created FastSpeech 2?

FastSpeech 2 was published by Zhejiang University (ZJU),Microsoft Research Asia, based in China, categorised as academia,Industry.

Source

Original publication

Record last updated 28 November 2025

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.