Merge branch 'master' of ssh://invmac/~/Public/repos/speech-scoring

speech_samplegen.py

@@ -5,7 +5,6 @@ from Foundation import NSURL
 import json
 import csv
 import random
-import string
 import os
 import re
 import subprocess
@@ -13,36 +12,12 @@ import time
 from tqdm import tqdm
 
 from generate_similar import similar_phoneme_phrase,similar_phrase
+from speech_tools import hms_string,create_dir,format_filename
 
 OUTPUT_NAME = 'story_phrases'
 dest_dir = os.path.abspath('.') + '/outputs/' + OUTPUT_NAME + '/'
 dest_file = './outputs/' + OUTPUT_NAME + '.csv'
 
-def hms_string(sec_elapsed):
-    h = int(sec_elapsed / (60 * 60))
-    m = int((sec_elapsed % (60 * 60)) / 60)
-    s = sec_elapsed % 60.
-    return "{}:{:>02}:{:>05.2f}".format(h, m, s)
-
-def create_dir(direc):
-    if not os.path.exists(direc):
-        os.makedirs(direc)
-
-def format_filename(s):
-    """
-    Take a string and return a valid filename constructed from the string.
-    Uses a whitelist approach: any characters not present in valid_chars are
-    removed. Also spaces are replaced with underscores.
-
-    Note: this method may produce invalid filenames such as ``, `.` or `..`
-    When I use this method I prepend a date string like '2009_01_15_19_46_32_'
-    and append a file extension like '.txt', so I avoid the potential of using
-    an invalid filename.
-    """
-    valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
-    filename = ''.join(c for c in s if c in valid_chars)
-    filename = filename.replace(' ','_') # I don't like spaces in filenames.
-    return filename
 
 def dest_filename(w, v, r, t):
     rand_no = str(random.randint(0, 10000))

speech_segmentgen.py

@@ -10,9 +10,7 @@ import json
 import csv
 import subprocess
 from tqdm import tqdm
-
+from speech_tools import create_dir,format_filename
-from speech_samplegen import SynthVariant, format_filename
-from speech_tools import create_dir
 
 apple_phonemes = [
     '%', '@', 'AE', 'EY', 'AO', 'AX', 'IY', 'EH', 'IH', 'AY', 'IX', 'AA', 'UW',
@@ -20,7 +18,7 @@ apple_phonemes = [
     'l', 'm', 'n', 'N', 'p', 'r', 's', 'S', 't', 'T', 'v', 'w', 'y', 'z', 'Z'
 ]
 
-OUTPUT_NAME = 'story_phrases_segments'
+OUTPUT_NAME = 'story_test_segments'
 
 dest_dir = os.path.abspath('.') + '/outputs/' + OUTPUT_NAME + '/'
 csv_dest_file = os.path.abspath('.') + '/outputs/' + OUTPUT_NAME + '.csv'
@@ -58,7 +56,10 @@ class Delegate (NSObject):
     def applicationDidFinishLaunching_(self, aNotification):
         '''Called automatically when the application has launched'''
         print("App Launched!")
-        generate_audio()
+        # phrases = story_texts()#random.sample(story_texts(), 100)  #
+        phrases = test_texts(30)
+        # print(phrases)
+        generate_audio(phrases)
 
 
 class PhonemeTiming(object):
@@ -181,10 +182,13 @@ def story_texts():
     text_list = sorted(list(set(text_list_dup)))
     return text_list
 
+def test_texts(count=10):
+    word_list = [i.strip('\n_') for i in open('./inputs/wordlist.txt','r').readlines()]
+    text_list = sorted(random.sample(list(set(word_list)),count))
+    return text_list
 
-def generate_audio():
+def generate_audio(phrases):
     synthQ = SynthesizerQueue()
-    phrases = story_texts()#random.sample(story_texts(), 100)  # 
     f = open(csv_dest_file, 'w')
     s_csv_w = csv.writer(f, quoting=csv.QUOTE_MINIMAL)
     i = 0

speech_tools.py

@@ -1,5 +1,6 @@
 import os
 import math
+import string
 import threading
 import multiprocessing
 import pandas as pd
@@ -101,10 +102,15 @@ def apply_by_multiprocessing(df,func,**kwargs):
 def square(x):
     return x**x
 
-if __name__ == '__main__':
+# if __name__ == '__main__':
-    df = pd.DataFrame({'a':range(10), 'b':range(10)})
+#     df = pd.DataFrame({'a':range(10), 'b':range(10)})
-    apply_by_multiprocessing(df, square, axis=1, workers=4)
+#     apply_by_multiprocessing(df, square, axis=1, workers=4)
 
+def hms_string(sec_elapsed):
+    h = int(sec_elapsed / (60 * 60))
+    m = int((sec_elapsed % (60 * 60)) / 60)
+    s = sec_elapsed % 60.
+    return "{}:{:>02}:{:>05.2f}".format(h, m, s)
 
 def rm_rf(d):
     for path in (os.path.join(d,f) for f in os.listdir(d)):
@@ -122,6 +128,22 @@ def create_dir(direc):
         create_dir(direc)
 
 
+def format_filename(s):
+    """
+    Take a string and return a valid filename constructed from the string.
+    Uses a whitelist approach: any characters not present in valid_chars are
+    removed. Also spaces are replaced with underscores.
+
+    Note: this method may produce invalid filenames such as ``, `.` or `..`
+    When I use this method I prepend a date string like '2009_01_15_19_46_32_'
+    and append a file extension like '.txt', so I avoid the potential of using
+    an invalid filename.
+    """
+    valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
+    filename = ''.join(c for c in s if c in valid_chars)
+    filename = filename.replace(' ','_') # I don't like spaces in filenames.
+    return filename
+
 #################### Now make the data generator threadsafe ####################
 
 class threadsafe_iter: