mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix #284; BiRNN with stride 2

Browse Source
This commit is contained in:
Tilman Kamp 2016-12-19 16:21:39 +01:00
parent 7cc75f252f
commit 8e99eeffdd
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
util/audio.py
View File

@ -10,6 +10,9 @@ def audiofile_to_input_vector(audio_filename, numcep, numcontext):
# Get mfcc coefficients
orig_inputs = mfcc(audio, samplerate=fs, numcep=numcep)
# We only keep every second feature (BiRNN stride = 2)
orig_inputs = orig_inputs[::2]
# For each time slice of the training set, we need to copy the context this makes
# the numcep dimensions vector into a numcep + 2*numcep*numcontext dimensions
# because of: