# How to build a bi-LSTM in Flux.jl 0.14

**URL:** <https://discourse.julialang.org/t/how-to-build-a-bi-lstm-in-flux-jl-0-14/115114>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [June 3, 2024, 11:28am UTC](https://discourse.julialang.org/t/how-to-build-a-bi-lstm-in-flux-jl-0-14/115114 "2024-06-03T11:28:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![NeroBlackstone](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/neroblackstone/32/208679_2.png) [@NeroBlackstone](https://discourse.julialang.org/u/NeroBlackstone)\
**Post date:** [June 3, 2024, 11:28am UTC](https://discourse.julialang.org/t/how-to-build-a-bi-lstm-in-flux-jl-0-14/115114/1 "2024-06-03T11:28:03Z")

</div>

There is currently a [wrapper layer](https://github.com/FluxML/Flux.jl/pull/1790/files) waiting to be merged, but it has not been updated in several years.

There is also an early speech recognition example in the Model Zoo, but it only supports [Flux 0.6](https://github.com/FluxML/model-zoo/tree/master/contrib/audio/speech-blstm) and [Flux 0.10](https://github.com/FluxML/model-zoo/pull/179).

So, How to build a bi-LSTM in Flux.jl 0.14?