SauTech
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
- Saudi Data and Artificial Intelligence Authority,Saudi Company for Artificial Intelligence
- Organisation type
- Industry,Government,Industry,Government
- Country
- Saudi Arabia
- Published
- 14 September 2022
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech, Audio
- Task
- Speech recognition (ASR), Speech-to-text
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
- tokens
The model has been trained on approximately 16k hours of dialectal Arabic speech. The total number of datasets is 8. The training data was balanced, with approximately 2,000 hours representing each dialect.
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
- 8
- Wall-clock time
- 720 hours (30 days)
- Power draw
- 6.4 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
- Hosted access (no API)
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
The model outperforms the next best system by approximately 8% and 9% on Modern Standard Arabic and Saudi dialects respectively. They don't report any results on standard benchmarks
Sources
Where this record came from and when it was last checked.
- Reference
- SDAIA and SCAI Unveil "SauTech" Speech-to-text Software
- Last updated
- 28 November 2025
What the numbers mean
What this model is
SauTech was published by Saudi Data and Artificial Intelligence Authority,Saudi Company for Artificial Intelligence, in the country recorded as Saudi Arabia, during September 2022. The publishing organisation is categorised as industry,Government,Industry,Government.
It works in the domain of Speech, Audio, and is recorded as performing the task of speech recognition (ASR), Speech-to-text.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
The reason it appears in this catalogue at all: sOTA improvement.
Answers
SauTech — common questions
SauTech— 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.
SauTech— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
SauTech— 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.
SauTech— who created it?
It was published by Saudi Data and Artificial Intelligence Authority,Saudi Company for Artificial Intelligence, based in Saudi Arabia, an organisation categorised as industry,Government,Industry,Government.
SauTech— when was it released?
It was published in September 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.
SauTech— what is it used for?
It works in the domain of Speech, Audio, and is recorded as handling the task of speech recognition (ASR), Speech-to-text. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
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.