HAM-TTS
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
- Geely Automobile Research Institute (Ningbo) Company,National Institute of Informatics,Shanghai Jiao Tong University
- Organisation type
- Industry,Academia
- Country
- China, Japan
- Published
- 9 March 2024
- Authors
- Chunhui Wang, Chang Zeng, Bowen Zhang, Ziyang Ma, Yefan Zhu, Zifeng Cai, Jian Zhao, Zhonglin Jiang, Yong Chen
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), 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
- 800M
- Training data
- tokens
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 A100
- Chips used
- 512
- Power draw
- 405.2 kW
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
demo page: https://anonymous.4open.science/w/ham-tts/
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
HAM-TTS was published by Geely Automobile Research Institute (Ningbo) Company,National Institute of Informatics,Shanghai Jiao Tong University, in China, in March 2024. The organisation is categorised as industry,Academia.
It works in Speech, and is recorded as doing text-to-speech (TTS), Speech synthesis.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
HAM-TTS — common questions
Is HAM-TTS open source?
No. HAM-TTS has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does HAM-TTS have?
HAM-TTS has 800M parameters. 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 HAM-TTS?
HAM-TTS was published by Geely Automobile Research Institute (Ningbo) Company,National Institute of Informatics,Shanghai Jiao Tong University, based in China, categorised as industry,Academia.
When was HAM-TTS released?
HAM-TTS was published in March 2024. 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 HAM-TTS used for?
HAM-TTS works in Speech, and is recorded as handling text-to-speech (TTS), Speech synthesis. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run HAM-TTS?
None. HAM-TTS 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.