top-down frozen classifier
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
- University of Edinburgh,Toshiba Cambridge Research Laboratory
- Organisation type
- Academia,Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 9 February 2021
- Authors
- Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Speech recognition (ASR)
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
- 3,408,000 tokens
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.
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
- Citations
- 2
- Benchmark data
- top-down frozen classifier
"Table 2 demonstrates that, to the best of our knowledge, top-down training results in state-of-the art character error rates for LSTM-based endto-end models on WSJ"
Sources
Where this record came from and when it was last checked.
- Reference
- Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
- Last updated
- 28 November 2025
What the numbers mean
What this model is
top-down frozen classifier was published by University of Edinburgh,Toshiba Cambridge Research Laboratory, in United Kingdom of Great Britain and Northern Ireland, in February 2021. The organisation is categorised as academia,Industry.
It works in Speech, and is recorded as doing speech recognition (ASR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training set ran to roughly 3,408,000 tokens.
Its inclusion criterion is sOTA improvement.
Answers
top-down frozen classifier — common questions
When was top-down frozen classifier released?
top-down frozen classifier was published in February 2021. 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 top-down frozen classifier used for?
top-down frozen classifier works in Speech, and is recorded as handling speech recognition (ASR). 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.
What GPU do I need to run top-down frozen classifier?
None. top-down frozen classifier 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 top-down frozen classifier open source?
No. top-down frozen classifier has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does top-down frozen classifier have?
No parameter count has been published for top-down frozen classifier, which is why no memory or speed figure appears on this page.
Who created top-down frozen classifier?
top-down frozen classifier was published by University of Edinburgh,Toshiba Cambridge Research Laboratory, based in United Kingdom of Great Britain and Northern Ireland, 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.