Created
March 22, 2017 22:38
-
-
Save mrubash1/616d8af4a4388dd5a055fca71a3cd101 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Load wav files | |
fs, audio = wav.read(audio_filename) | |
# Get mfcc coefficients | |
orig_inputs = mfcc(audio, samplerate=fs, numcep=numcep) | |
# For each time slice of the training set, we need to copy the context this makes | |
train_inputs = np.array([], np.float32) | |
train_inputs.resize((orig_inputs.shape[0], numcep + 2 * numcep * numcontext)) | |
for time_slice in range(train_inputs.shape[0]): | |
# Pick up to numcontext time slices in the past, | |
# And complete with empty mfcc features | |
need_empty_past = max(0, ((time_slices[0] + numcontext) - time_slice)) | |
empty_source_past = list(empty_mfcc for empty_slots in range(need_empty_past)) | |
data_source_past = orig_inputs[max(0, time_slice - numcontext):time_slice] | |
assert(len(empty_source_past) + len(data_source_past) == numcontext) | |
... |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment