|
@@ -25,17 +25,14 @@ for a in range(0, len(df), slices_length):
|
|
|
#finds the segment offset of the 100th transcription entry and stores it into var
|
|
|
#in milliseconds
|
|
|
audio_offset = df_sliced['segment_offset'].max()
|
|
|
-
|
|
|
- #finds the segment offset of the 100th transcription entry and stores it into var
|
|
|
- #in milliseconds
|
|
|
- audio_offset = int(df_sliced.tail(1)['segment_offset'])
|
|
|
-
|
|
|
+
|
|
|
#extracts recording at desired length and exports it to new file
|
|
|
recording_sliced = recording[audio_onset:audio_offset]
|
|
|
- recording_sliced.export("outputs/csv2grid_output/BN{0}.wav".format(a), format='wav')
|
|
|
+ recording_sliced.export("outputs/csv2grid_output/BN-{0}-{1}.wav".format(audio_onset, audio_offset), format='wav')
|
|
|
|
|
|
#create textgrid
|
|
|
grid = pr.TextGrid(xmax = (audio_offset-audio_onset)/1000)
|
|
|
+
|
|
|
#iterate through each row
|
|
|
for speaker, segments in df_sliced.groupby('speaker_id'):
|
|
|
aTier = grid.add_tier(speaker)
|
|
@@ -52,7 +49,7 @@ for a in range(0, len(df), slices_length):
|
|
|
False
|
|
|
)
|
|
|
|
|
|
- grid.to_file("outputs/csv2grid_output/BN{0}.TextGrid".format(a))
|
|
|
+ grid.to_file("outputs/csv2grid_output/BN-{0}-{1}.TextGrid".format(audio_onset, audio_offset))
|
|
|
|
|
|
|
|
|
#the end cut for this iteration becomes the starting point for next iteration
|