DBLSTM

Closed weights University of Toronto 29.9M parameters December 2013

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 Toronto
Organisation type
Academia
Country
Canada
Published
8 December 2013
Authors
A Graves, N Jaitly, A Mohamed

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
29.9M

"The DBLSTM network had five bidirectional hidden levels, with 500 LSTM cells in each of the forward and backward layers, and a size 3385 softmax output layer, giving a total of 29.9M weights."

Training data
5,040,000 tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Citations
1,597

Sources

Where this record came from and when it was last checked.

Reference
Hybrid speech recognition with Deep Bidirectional LSTM
Last updated
28 November 2025

What the numbers mean

Background

DBLSTM was published by University of Toronto, in the country recorded as Canada, during December 2013. The publishing organisation is categorised as 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.

What went into building it

It was trained on a corpus of about 5,040,000 tokens of text.

Answers

DBLSTM — common questions

01

DBLSTM— when was it released?

It was published in December 2013. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

DBLSTM— what is it used for?

It works in the domain of Speech, and is recorded as handling the task of 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.

03

DBLSTM— 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.

04

DBLSTM— 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.

05

DBLSTM— how many parameters does it have?

It has a parameter count of 29.9M. "The DBLSTM network had five bidirectional hidden levels, with 500 LSTM cells in each of the forward and backward layers, and a size 3385 softmax output layer, giving a total of 29.9M 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.

06

DBLSTM— who created it?

It was published by University of Toronto, based in Canada, an organisation categorised as academia.

Source

Original publication

Record last updated 28 November 2025

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.