Deep speech Uni/Bidirectional LSTM?

Deep Speech
#1

Hi
Is the LSTM layer in Deep Speech v0.6 Unidirectional or Bidirectional?
According to Baidu’s paper, it is bidirectional, but it seems to be unidirectional in Mozilla’s Deep Speech.
Is that correct?

#2

That’s correct, this is what we document on https://deepspeech.readthedocs.io/en/v0.6.0/DeepSpeech.html. Please send PR / issues if you think the wording of the documentation needs improvement.

1 Like
#3

Thank you for your fast response.

That’s correct

That leads to another question.
Why Deep Speech cannot generate output in real-time?
Why does it need to get the whole audio file to generates output?

#4

DeepSpeech is capable of streaming and can generate output faster than real time with appropriate hardware. We have extensive documentation on the streaming API as well as several examples.

1 Like