bobby/open_dbm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

derived logic update

Browse Source
This commit is contained in:
Vijay Yadev
2020-08-05 16:00:21 -04:00
parent c389fc2c47
commit 7bdf6b891a
19 changed files with 319 additions and 245 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
dbm_lib/dbm_features/raw_features/audio/formant_freq.py
View File

@@ -109,17 +109,21 @@ def run_formant(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_fm(video_uri, out_loc, fl_name, r_config)
return
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
calc_formant(video_uri, audio_file, out_loc, fl_name, r_config)
empty_fm(video_uri, out_loc, fl_name, r_config)
return
calc_formant(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

28
dbm_lib/dbm_features/raw_features/audio/gne.py
View File

@@ -140,18 +140,22 @@ def run_gne(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_gne(video_uri, out_loc, fl_name, r_config, error_txt)
return
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
calc_gne(video_uri, audio_file, out_loc, fl_name, r_config)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_gne(video_uri, out_loc, fl_name, r_config, error_txt)
return
calc_gne(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

26
dbm_lib/dbm_features/raw_features/audio/hnr.py
View File

@@ -76,17 +76,21 @@ def run_hnr(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_hnr(video_uri, out_loc, fl_name, r_config)
return
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
calc_hnr(video_uri, audio_file, out_loc, fl_name, r_config)
empty_hnr(video_uri, out_loc, fl_name, r_config)
return
calc_hnr(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

26
dbm_lib/dbm_features/raw_features/audio/intensity.py
View File

@@ -72,17 +72,21 @@ def run_intensity(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_intensity(video_uri, out_loc, fl_name, r_config)
return
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
calc_intensity(video_uri, audio_file, out_loc, fl_name, r_config)
empty_intensity(video_uri, out_loc, fl_name, r_config)
return
calc_intensity(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

26
dbm_lib/dbm_features/raw_features/audio/jitter.py
View File

@@ -138,18 +138,22 @@ def run_jitter(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_jitter(video_uri, out_loc, fl_name, r_config, error_txt)
return
error_txt = 'error: length less than 0.064'
empty_jitter(video_uri, out_loc, fl_name, r_config, error_txt)
return
calc_jitter(video_uri, audio_file, out_loc, fl_name, r_config)
calc_jitter(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

31
dbm_lib/dbm_features/raw_features/audio/mfcc.py
View File

@@ -85,18 +85,21 @@ def run_mfcc(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_mfcc(video_uri, out_loc, fl_name, r_config)
return
calc_mfcc(video_uri, audio_file, out_loc, fl_name, r_config)
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_mfcc(video_uri, out_loc, fl_name, r_config)
return
calc_mfcc(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

71
dbm_lib/dbm_features/raw_features/audio/pause_segment.py
View File

@@ -131,37 +131,42 @@ def run_pause_segment(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_pause_segment(video_uri, out_loc, fl_name, r_config, error_txt)
return
logger.info('Converting stereo sound to mono-lD')
sound_mono = AudioSegment.from_wav(audio_file)
sound_mono = sound_mono.set_channels(1)
sound_mono = sound_mono.set_frame_rate(48000)
mono_wav = os.path.join(input_loc, fl_name + '_mono.wav')
sound_mono.export(mono_wav, format="wav")
df_pause_seg = process_silence(mono_wav, r_config)
os.remove(mono_wav)#removing mono wav file
try:
if isinstance(df_pause_seg, pd.DataFrame) and len(df_pause_seg)>0:
logger.info('Processing Output file {} '.format(out_loc))
df_pause_seg['dbm_master_url'] = video_uri
ut.save_output(df_pause_seg, out_loc, fl_name, pause_seg_dir, csv_ext)
else:
error_txt = 'error: webrtcvad returns no segment'
empty_pause_segment(video_uri, out_loc, fl_name, r_config, error_txt)
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_pause_segment(video_uri, out_loc, fl_name, r_config, error_txt)
return
logger.info('Converting stereo sound to mono-lD')
sound_mono = AudioSegment.from_wav(audio_file)
sound_mono = sound_mono.set_channels(1)
sound_mono = sound_mono.set_frame_rate(48000)
mono_wav = os.path.join(input_loc, fl_name + '_mono.wav')
sound_mono.export(mono_wav, format="wav")
df_pause_seg = process_silence(mono_wav, r_config)
os.remove(mono_wav)#removing mono wav file
if isinstance(df_pause_seg, pd.DataFrame) and len(df_pause_seg)>0:
logger.info('Processing Output file {} '.format(out_loc))
df_pause_seg['dbm_master_url'] = video_uri
ut.save_output(df_pause_seg, out_loc, fl_name, pause_seg_dir, csv_ext)
else:
error_txt = 'error: webrtcvad returns no segment'
empty_pause_segment(video_uri, out_loc, fl_name, r_config, error_txt)
except Exception as e:
logger.error('Failed to process audio file')

26
dbm_lib/dbm_features/raw_features/audio/pitch_freq.py
View File

@@ -93,17 +93,21 @@ def run_pitch(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_pitch(video_uri, out_loc, fl_name, r_config)
return
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
calc_pitch(video_uri, audio_file, out_loc, fl_name, r_config)
empty_pitch(video_uri, out_loc, fl_name, r_config)
return
calc_pitch(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

29
dbm_lib/dbm_features/raw_features/audio/shimmer.py
View File

@@ -139,19 +139,22 @@ def run_shimmer(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
error_txt = 'error: length less than 0.064'
empty_shimmer(video_uri, out_loc, fl_name, r_config, error_txt)
return
calc_shimmer(video_uri, audio_file, out_loc, fl_name, r_config)
error_txt = 'error: length less than 0.064'
empty_shimmer(video_uri, out_loc, fl_name, r_config, error_txt)
return
calc_shimmer(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')

26
dbm_lib/dbm_features/raw_features/audio/voice_frame_score.py
View File

@@ -91,17 +91,21 @@ def run_vfs(video_uri, out_dir, r_config):
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
try:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter)>0:
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_vfs(video_uri, out_loc, fl_name, r_config)
return
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
calc_vfs(video_uri, audio_file, out_loc, fl_name, r_config)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(audio_file))
empty_vfs(video_uri, out_loc, fl_name, r_config)
return
calc_vfs(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')