search

philipperemy / tensorflow-ctc-speech-recognition

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).
Apache License 2.0
130 stars 46 forks source link

What does number of feature do? #5

Closed gabegaz closed 5 years ago

gabegaz commented 6 years ago

Thanks philipperemy for this work,

1) What does number of features do? Couldnot understand that

2) I just want to the number of layers to something like 4 or 5 but there is a dimension issue. Is there any other adjustment i should make other than increase the number of layers?

Thanks

philipperemy commented 5 years ago

@getabegaz thank you!

  1. It's the number of features for each timestep. In this case it's the number of MFCCs.
  2. Yeah seems like there's a dimension issue. I'll search for a way to fix it.
philipperemy commented 5 years ago

Well dynamic_rnn is deprecated anyway. So I guess it's better to upgrade the APIs to V2. I'll try to find some time to do that.