def predict_from_textgrid(wav_filename, preds_filename, textgrid_filename, textgrid_tier):
print wav_filename
if os.path.exists(preds_filename):
os.remove(preds_filename)
textgrid = TextGrid()
# read TextGrid
textgrid.read(textgrid_filename)
# extract tier names
tier_names = textgrid.tierNames()
if textgrid_tier in tier_names:
tier_index = tier_names.index(textgrid_tier)
# run over all intervals in the tier
for interval in textgrid[tier_index]:
if re.search(r'\S', interval.mark()):
tmp_features_filename = generate_tmp_filename("features")
tmp_preds = generate_tmp_filename("preds")
features.create_features(wav_filename, tmp_features_filename, interval.xmin(), interval.xmax())
easy_call("th load_estimation_model.lua " + tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)
else: # process first tier
for interval in textgrid[0]:
if re.search(r'\S', interval.mark()):
tmp_features_filename = generate_tmp_filename("features")
tmp_preds = generate_tmp_filename("preds")
features.create_features(wav_filename, tmp_features_filename, interval.xmin(), interval.xmax())
easy_call("th load_estimation_model.lua " + tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)
def predict_from_times(wav_filename, preds_filename, begin, end):
tmp_features_filename = tempfile._get_default_tempdir() + "/" + next(tempfile._get_candidate_names()) + ".txt"
print tmp_features_filename
if begin > 0.0 or end > 0.0:
features.create_features(wav_filename, tmp_features_filename, begin, end)
easy_call("th load_estimation_model.lua " + tmp_features_filename + ' ' + preds_filename)
else:
features.create_features(wav_filename, tmp_features_filename)
easy_call("th load_tracking_model.lua " + tmp_features_filename + ' ' + preds_filename)
def predict_from_times(wav_filename, preds_filename, begin, end):
tmp_features_filename = tempfile._get_default_tempdir() + "/" + next(
tempfile._get_candidate_names()) + ".txt"
print tmp_features_filename
if begin > 0.0 or end > 0.0:
features.create_features(wav_filename, tmp_features_filename, begin,
end)
easy_call("th load_estimation_model.lua " + tmp_features_filename +
' ' + preds_filename)
else:
features.create_features(wav_filename, tmp_features_filename)
easy_call("th load_tracking_model.lua " + tmp_features_filename + ' ' +
preds_filename)
def predict_from_textgrid(wav_filename, preds_filename, textgrid_filename,
textgrid_tier):
print wav_filename
if os.path.exists(preds_filename):
os.remove(preds_filename)
textgrid = TextGrid()
# read TextGrid
textgrid.read(textgrid_filename)
# extract tier names
tier_names = textgrid.tierNames()
if textgrid_tier in tier_names:
tier_index = tier_names.index(textgrid_tier)
# run over all intervals in the tier
for interval in textgrid[tier_index]:
if re.search(r'\S', interval.mark()):
print interval.mark()
tmp_features_filename = generate_tmp_filename("features")
tmp_preds = generate_tmp_filename("preds")
features.create_features(wav_filename, tmp_features_filename,
interval.xmin(), interval.xmax())
easy_call("th load_estimation_model.lua " +
tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)
else: # process first tier
for interval in textgrid[0]:
if re.search(r'\S', interval.mark()):
tmp_features_filename = generate_tmp_filename("features")
tmp_preds = generate_tmp_filename("preds")
features.create_features(wav_filename, tmp_features_filename,
interval.xmin(), interval.xmax())
easy_call("th load_estimation_model.lua " +
tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)