BLSTM for handwriting (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
- University of Bern,IDSIA,Technical University of Munich
- Organisation type
- Academia,Academia,Academia
- Country
- Switzerland, Germany
- Published
- 3 December 2007
- Authors
- Alex Graves, Marcus Liwicki, Horst Bunke, Jürgen Schmidhuber, Santiago Fernández
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Character recognition (OCR)
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
- 100.9K
- Training data
- 3,298,424 tokens
For the raw input representation, there were 4 input units and a total of 100,881 weights
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
- Citations
- 341
"In experiments on an unconstrained online database, we record excellent results using either raw or preprocessed data, well outperforming a state-of-the-art HMM based system in both cases."
Sources
Where this record came from and when it was last checked.
- Reference
- Unconstrained online handwriting recognition with recurrent neural networks
- Last updated
- 11 February 2026
What the numbers mean
About this model
BLSTM for handwriting (2) was published by University of Bern,IDSIA,Technical University of Munich, in Switzerland, in December 2007. The organisation is categorised as academia,Academia,Academia.
It works in Vision, and is recorded as doing character recognition (OCR).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Around 3,298,424 tokens went into training it.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
BLSTM for handwriting (2) — common questions
When was BLSTM for handwriting (2) released?
BLSTM for handwriting (2) was published in December 2007. 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 BLSTM for handwriting (2) used for?
BLSTM for handwriting (2) works in Vision, and is recorded as handling character recognition (OCR). These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run BLSTM for handwriting (2)?
None. BLSTM for handwriting (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 BLSTM for handwriting (2) open source?
The licensing for BLSTM for handwriting (2) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does BLSTM for handwriting (2) have?
BLSTM for handwriting (2) has 100.9K parameters. For the raw input representation, there were 4 input units and a total of 100,881 weights. 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 BLSTM for handwriting (2)?
BLSTM for handwriting (2) was published by University of Bern,IDSIA,Technical University of Munich, based in Switzerland, categorised as academia,Academia,Academia.
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.