# Is there a sample code for BiLSTM?
**URL:** https://discourse.julialang.org/t/is-there-a-sample-code-for-bilstm/28749
**Category:** New to Julia
**Tags:** flux
**Created:** [September 14, 2019, 2:24am UTC](https://discourse.julialang.org/t/is-there-a-sample-code-for-bilstm/28749 "2019-09-14T02:24:56Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@yeruoforever](https://discourse.julialang.org/u/yeruoforever)
#### Post date: [September 14, 2019, 2:24am UTC](https://discourse.julialang.org/t/is-there-a-sample-code-for-bilstm/28749/1 "2019-09-14T02:24:56Z")
I am a ML beginner,I almost finished reading the documents about [Flux.jl](https://pkg.julialang.org/docs/Flux/QdkVy/0.9.0),but I have no idea about implementing a Bi-directional LSTM using native’s Flux.jl.😰
---
### Author:  [@yeruoforever](https://discourse.julialang.org/u/yeruoforever)
#### Post date: [September 15, 2019, 3:48am UTC](https://discourse.julialang.org/t/is-there-a-sample-code-for-bilstm/28749/2 "2019-09-15T03:48:11Z")
I found a tutorial in [FluxML/model-zoo](https://github.com/FluxML/model-zoo/tree/master/audio/speech-blstm).
It is an implementation of the neural network for speech recognition described in Graves & Schmidhuber (2005). It takes in frames of frequency information derived from the waveform, and it predicts which phone class the frame belongs to, among a reduced set of English phones. The training is run using the [TIMIT data set (Garofolo et al., 1993)](https://catalog.ldc.upenn.edu/LDC93S1).
---
### Author:  [@usmcamp0811](https://discourse.julialang.org/u/usmcamp0811)
#### Post date: [March 15, 2021, 3:44pm UTC](https://discourse.julialang.org/t/is-there-a-sample-code-for-bilstm/28749/3 "2021-03-15T15:44:04Z")
same boat as the OP and I just wanted to update the url for the example as they’ve moved somethings around in the model-zoo…
new location -\>\> [model-zoo/01-speech-blstm.jl at master · FluxML/model-zoo · GitHub](https://github.com/FluxML/model-zoo/blob/master/contrib/audio/speech-blstm/01-speech-blstm.jl)