azalea/DeepFormants
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

text grid integration; temp file management

Browse Source
This commit is contained in:
Jason
2022-04-03 11:25:18 -07:00
parent 906d649a39
commit ca26e3f058
5 changed files with 42 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+1
View File
@@ -5,3 +5,4 @@ data/*.*
output/*.*
tracking_model.dat
tracking_model.dat.gz
temp/*.*
extract_features.py
+4 -3
View File
@@ -4,15 +4,12 @@ import argparse
import numpy as np
import wave
import os
from os import listdir
from os.path import isfile, join
import math
from scipy.fftpack.realtransforms import dct
from scipy.signal import lfilter, hamming
from scipy.fftpack import fft, ifft
#from scikits.talkbox.linpred import lpc # obsolete
from helpers.conch_lpc import lpc
import shutil
from helpers.utilities import *
epsilon = 0.0000000001
@@ -274,6 +271,7 @@ def create_features(input_wav_filename, feature_filename, begin=None, end=None,
arr = [input_wav_filename]
arr.extend(build_single_feature_row(X, Atal))
np.savetxt(feature_filename, np.asarray([arr]), delimiter=",", fmt="%s")
os.remove(tmp_wav16_filename)
return arr
arcep_mat = []
for i in range(len(X)):
@@ -281,6 +279,9 @@ def create_features(input_wav_filename, feature_filename, begin=None, end=None,
arr.extend(build_single_feature_row(X[i], Atal))
arcep_mat.append(arr)
np.savetxt(feature_filename, np.asarray(arcep_mat), delimiter=",", fmt="%s")
os.remove(tmp_wav16_filename)
return arcep_mat
formants.py
+24 -22
View File
@@ -1,4 +1,3 @@
from json import load
import extract_features as features
import argparse
from helpers.textgrid import *
@@ -7,17 +6,19 @@ from load_estimation_model import load_estimation_model
def predict_from_times(wav_filename, preds_filename, begin, end):
tmp_features_filename = tempfile._get_default_tempdir() + "/" + next(tempfile._get_candidate_names()) + ".txt"
tmp_features_filename = "temp/" + next(tempfile._get_candidate_names()) + ".txt"
print("Input Array Path: " + tmp_features_filename)
if begin > 0.0 or end > 0.0:
print(wav_filename + " interval " + str(begin) + "-" + str(end) + ":")
features.create_features(wav_filename, tmp_features_filename, begin, end)
load_estimation_model(tmp_features_filename, preds_filename)
load_estimation_model(tmp_features_filename, preds_filename, begin, end)
#easy_call("luajit load_estimation_model.lua " + tmp_features_filename + ' ' + preds_filename)
else:
features.create_features(wav_filename, tmp_features_filename)
easy_call("luajit load_tracking_model.lua " + tmp_features_filename + ' ' + preds_filename)
delete_temp_files()
def predict_from_textgrid(wav_filename, preds_filename, textgrid_filename, textgrid_tier):
@@ -34,26 +35,27 @@ def predict_from_textgrid(wav_filename, preds_filename, textgrid_filename, textg
# extract tier names
tier_names = textgrid.tierNames()
if textgrid_tier in tier_names:
if textgrid_tier in tier_names: # run over all intervals in the tier
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())
load_estimation_model(tmp_features_filename, tmp_preds)
#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())
load_estimation_model(tmp_features_filename, tmp_preds)
#easy_call("th load_estimation_model.lua " + tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)
textgrid_tier = textgrid[tier_index]
else: # process first tier
textgrid_tier = textgrid[0]
for interval in textgrid_tier:
if re.search(r'\S', interval.mark()):
tmp_features_filename = generate_tmp_filename("features")
tmp_preds = generate_tmp_filename("preds")
begin = interval.xmin()
end = interval.xmax()
features.create_features(wav_filename, tmp_features_filename, begin, end)
load_estimation_model(tmp_features_filename, tmp_preds, begin, end)
#easy_call("th load_estimation_model.lua " + tmp_features_filename + ' ' + tmp_preds)
csv_append_row(tmp_preds, preds_filename)
delete_temp_files()
delete_temp_files()
if __name__ == "__main__":
# parse arguments
helpers/utilities.py
+8 -1
View File
@@ -25,6 +25,8 @@ import wave
import tempfile
import os
from isort import file
def csv_append_row(tmp_preds, preds_filename, with_headers=True):
@@ -55,7 +57,7 @@ def csv_append_row(tmp_preds, preds_filename, with_headers=True):
def generate_tmp_filename(extension):
return tempfile._get_default_tempdir() + "/" + next(tempfile._get_candidate_names()) + "." + extension
return "temp/" + next(tempfile._get_candidate_names()) + "." + extension
def logging_defaults(logging_level="INFO"):
@@ -169,3 +171,8 @@ def is_valid_wav(filename):
or wav_file.getcomptype() != 'NONE':
return False
return True
def delete_temp_files():
print("Clearing temp files...")
for filename in os.listdir("temp"):
os.remove("temp/" + filename)
load_estimation_model.py
+5 -3
View File
@@ -26,7 +26,7 @@ class LambdaReduce(LambdaBase):
return reduce(self.lambda_func,self.forward_prepare(input))
def load_estimation_model(inputfilename, outputfilename):
def load_estimation_model(inputfilename, outputfilename, begin, end):
with open(inputfilename, "r") as rf:
contents = rf.read()
contents = contents.split(",")
@@ -54,5 +54,7 @@ def load_estimation_model(inputfilename, outputfilename):
my_prediction = model.forward(data)
with open(outputfilename, "w") as wf:
wf.write("NAME,F1,F2,F3,F4\n")
wf.write(name + "," + str(1000 * float(my_prediction[0][0])) + "," + str(1000 * float(my_prediction[0][1])) + "," + str(1000 * float(my_prediction[0][2])) + "," + str(1000 * float(my_prediction[0][3])))
wf.write("NAME,begin,end,F1,F2,F3,F4\n")
wf.write(name + "," + str(begin) + "," + str(end) + "," + \
str(1000 * float(my_prediction[0][0])) + "," + str(1000 * float(my_prediction[0][1])) + "," + \
str(1000 * float(my_prediction[0][2])) + "," + str(1000 * float(my_prediction[0][3])) + "\n")