Bidirectional RNN

Closed weights Advanced Telecommunications Research Institute 13K parameters November 1997

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
Advanced Telecommunications Research Institute
Organisation type
Industry
Country
Japan
Published
1 November 1997
Authors
M. Schuster, KK Paliwal

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
13K

Page 7: "The structures of all networks are adjusted so that each of them has about the same number of free parameters (approximately 13 000 here"

Training data
142,910 tokens

"the training data set consisting of 3696 sentences from 462 speakers" Assuming avg sentence length of 20 words 3696 * 20 total words

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
Highly cited
Citations
7,990

Sources

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

Reference
Bidirectional recurrent neural networks
Last updated
28 November 2025

What the numbers mean

Background

Bidirectional RNN was published by Advanced Telecommunications Research Institute, in Japan, in November 1997. industry is the category the publisher falls under.

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.

How it was trained

The training set ran to roughly 142,910 tokens.

It is tracked in the underlying dataset for one reason in particular: highly cited.

Answers

Bidirectional RNN — common questions

01

Is Bidirectional RNN open source?

The licensing for Bidirectional RNN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does Bidirectional RNN have?

Bidirectional RNN has 13K parameters. Page 7: "The structures of all networks are adjusted so that each of them has about the same number of free parameters (approximately 13 000 here". 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.

03

Who created Bidirectional RNN?

Bidirectional RNN was published by Advanced Telecommunications Research Institute, based in Japan, categorised as industry.

04

When was Bidirectional RNN released?

Bidirectional RNN was published in November 1997. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Bidirectional RNN used for?

Bidirectional RNN works in Speech, and is recorded as handling speech recognition (ASR). These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run Bidirectional RNN?

None. Bidirectional RNN 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.

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.