Improve Silero's Preprocessor to Handle Roman Numerals and Abbreviations Better

extensions/silero_tts/tts_preprocessor.py

@@ -7,7 +7,7 @@ alphabet_map = {
     "B": " Bee ",
     "C": " See ",
     "D": " Dee ",
-    "E": " II ",
+    "E": " Ii ",
     "F": " Eff ",
     "G": " Jee ",
     "H": " Eich ",
@@ -38,18 +38,64 @@ def preprocess(string):
     string = string.replace('“', '')
     string = string.replace('\n', ' ')
     string = remove_commas(string)
+    string = replace_roman(string)
     string = hyphen_range_to(string)
     string = num_to_words(string)
-    string = string.strip()
+
     # TODO Try to use a ML predictor to expand abbreviations. It's hard, dependent on context, and whether to actually
     # try to say the abbreviation or spell it out as I've done below is not agreed upon
 
     # For now, expand abbreviations to pronunciations
     string = replace_abbreviations(string)
 
+    string = string.strip()
     return string
 
 
+def remove_surrounded_chars(string):
+    # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
+    # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
+    return re.sub(r'\*[^*]*?(\*|$)', '', string)
+
+
+def replace_roman(string):
+    pattern = re.compile(r'\s[IVXLCDM]+[\s,.?!)"\'\]>]')
+    result = string
+    while True:
+        match = pattern.search(result)
+        if match is None:
+            break
+
+        start = match.start()
+        end = match.end()
+        result = result[0:start+1] + str(roman_to_int(result[start+1:end-1])) + result[end-1:len(result)]
+
+    return result
+
+
+def roman_to_int(s):
+    rom_val = {'I': 1, 'V': 5, 'X': 10, 'L': 50, 'C': 100, 'D': 500, 'M': 1000}
+    int_val = 0
+    for i in range(len(s)):
+        if i > 0 and rom_val[s[i]] > rom_val[s[i - 1]]:
+            int_val += rom_val[s[i]] - 2 * rom_val[s[i - 1]]
+        else:
+            int_val += rom_val[s[i]]
+    return int_val
+
+
+def hyphen_range_to(text):
+    pattern = re.compile(r'(\d+)[-–](\d+)')
+    result = pattern.sub(lambda x: x.group(1) + ' to ' + x.group(2), text)
+    return result
+
+
+def num_to_words(text):
+    pattern = re.compile(r'\d+')
+    result = pattern.sub(lambda x: num2words(int(x.group())), text)
+    return result
+
+
 def replace_abbreviations(string):
     pattern = re.compile(r'[\s("\'\[<][A-Z]{2,4}[\s,.?!)"\'\]>]')
     result = string
@@ -81,24 +127,6 @@ def match_mapping(char, result):
     return result + char
 
 
-def remove_surrounded_chars(string):
-    # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
-    # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
-    return re.sub(r'\*[^*]*?(\*|$)', '', string)
-
-
-def hyphen_range_to(text):
-    pattern = re.compile(r'(\d+)[-–](\d+)')
-    result = pattern.sub(lambda x: x.group(1) + ' to ' + x.group(2), text)
-    return result
-
-
-def num_to_words(text):
-    pattern = re.compile(r'\d+')
-    result = pattern.sub(lambda x: num2words(int(x.group())), text)
-    return result
-
-
 def remove_commas(text):
     import re
     pattern = re.compile(r'(\d),(\d)')