CTC-Trained LSTM
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
- IDSIA,Technical University of Munich
- Organisation type
- Academia,Academia
- Country
- Switzerland, Germany
- Published
- 25 June 2006
- Authors
- Alex Graves, Santiago Fernández, Faustino Gómez, Jürgen Schmidhuber
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.
- Parameters
- 114.7K
- Training data
- tokens
"The hidden layers were fully connected to themselves and the output layer, and fully connected from the input layer. The input layer was size 26, the softmax output layer size 62 (61 phoneme categories plus the blank label), and the total number of weights was 114, 662." https://www.cs.toronto.edu/~graves/icml_2006.pdf
4162 utterances, guesstimated avg 10 words per utterance
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 4,862
Sources
Where this record came from and when it was last checked.
- Reference
- Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
- Last updated
- 28 November 2025
What the numbers mean
Background
CTC-Trained LSTM was published by IDSIA,Technical University of Munich, in the country recorded as Switzerland, during June 2006. The publishing organisation is categorised as academia,Academia.
It works in the domain of Speech, and is recorded as performing the task of speech recognition (ASR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
CTC-Trained LSTM — common questions
CTC-Trained LSTM— 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.
CTC-Trained LSTM— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
CTC-Trained LSTM— how many parameters does it have?
It has a parameter count of 114.7K. "The hidden layers were fully connected to themselves and the output layer, and fully connected from the input layer. The input layer was size 26, the softmax output layer size 62 (61 phoneme categories plus the blank label), and the total number of weights was 114, 662." https://www.cs.toronto.edu/~graves/icml_2006.pdf. 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.
CTC-Trained LSTM— who created it?
It was published by IDSIA,Technical University of Munich, based in Switzerland, an organisation categorised as academia,Academia.
CTC-Trained LSTM— when was it released?
It was published in June 2006. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
CTC-Trained LSTM— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of speech recognition (ASR). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
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.