File size: 5,902 Bytes
9382c4c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e9c7026
9382c4c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94f2602
 
9382c4c
94f2602
9382c4c
 
94f2602
 
9382c4c
94f2602
9382c4c
94f2602
 
9382c4c
94f2602
9382c4c
 
94f2602
 
 
 
 
 
 
 
9382c4c
 
94f2602
 
9382c4c
 
 
94f2602
9382c4c
 
 
 
 
 
94f2602
 
9382c4c
 
 
 
 
 
 
 
 
94f2602
9382c4c
94f2602
 
 
9382c4c
94f2602
 
 
9382c4c
94f2602
9382c4c
 
 
1e668a5
9382c4c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
import argparse
import tempfile
import random
import re
import string
import subprocess
from typing import Optional
from TTS.config import load_config
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer

def sanitize_filename(filename):
    """Remove or replace any characters that are not allowed in file names."""
    return ''.join(c for c in filename if c.isalnum() or c in (' ', '_', '-')).rstrip()

# function to add original punctuation to cotovía numbers extension (option p)
def punctuate_p(str_ext):

    # substitute ' ·\n' by ...
    str_ext = re.sub(r" ·", r"...", str_ext)
    
    # remove spaces before , . ! ? ; : ) ] of the extended string
    str_ext = re.sub(r"\s+([.,!?;:)\]])", r"\1", str_ext)

    # remove spaces after ( [ ¡ ¿ of the extended string
    str_ext = re.sub(r"([\(\[¡¿])\s+", r"\1", str_ext)

    # remove unwanted spaces between quotations marks
    str_ext = re.sub(r'"\s*([^"]*?)\s*"', r'"\1"', str_ext)

    # substitute '- text -' to '-text-'
    str_ext = re.sub(r"-\s*([^-]*?)\s*-", r"-\1-", str_ext)

    # remove initial question marks
    str_ext = re.sub(r"[¿¡]", r"", str_ext)

    # eliminate extra spaces
    str_ext = re.sub(r"\s+", r" ", str_ext)

    str_ext = re.sub(r"(\d+)\s*-\s*(\d+)", r"\1 \2", str_ext)

    ### - , ' and () by commas
    # substitute '- text -' to ', text,'
    str_ext = re.sub(r"(\w+)\s+-([^-]*?)-\s+([^-]*?)", r"\1, \2, ", str_ext)

    # substitute ' - ' by ', '
    str_ext = re.sub(r"(\w+[!\?]?)\s+-\s*", r"\1, ", str_ext)

    # substitute ' ( text )' to ', text,'
    str_ext = re.sub(r"(\w+)\s*\(\s*([^\(\)]*?)\s*\)", r"\1, \2,", str_ext)


    return str_ext


def to_cotovia(text):
    ## Initial text preprocessing
    # substitute ' M€' by 'millóns de euros' and 'somewordM€' by 'someword millóns de euros'
    text = re.sub(r"(\w+)\s*M€", r"\1 millóns de euros", text)

    # substitute ' €' by 'euros' and 'someword€' by 'someword euros'
    text = re.sub(r"(\w+)\s*€", r"\1 euros", text)
    
    # substitute ' ºC' by 'graos centígrados' and 'somewordºC' by 'someword graos centígrados'
    text = re.sub(r"(\w+)\s*ºC", r"\1 graos centígrados", text)

    # Random string generation
    res = ''.join(random.choices(string.ascii_lowercase + string.digits, k=5))

    text = subprocess.run(["sed", "-e", "s/₂//g", "-e", "s/⸺//g", "-e", "s/ //g", "-e", "s///g", "-e", "s/č/c/g", "-e", "s/ț/t/g", "-e", "s/ğ/g/g", "-e", "s/ș/s/g",
                "-e", "s/ş/s/g", "-e", "s/Ž/Z/g", "-e", "s/ž/z/g", "-e", "s/ț/t/g", "-e", "s/ğ/g/g", "-e", "s/ș/s/g", "-e", "s/ş/s/g", "-e", "s/«//g", "-e", "s/»//g",
                "-e", "s/<<//g", "-e", "s/>>//g", "-e", "s/“/\"/g", "-e", "s/”/'\"'/g", "-e", "s/\'//g", "-e", "s/‘//g", "-e", "s/’//g", "-e", "s/…//g",
                "-e", "s/-/-/g", "-e", "s/–/-/g", "-e", "s/—/-/g", "-e", "s/―/-/g", "-e", "s/−/-/g", "-e", "s/‒/-/g", "-e", "s/─/-/g"],
                input = text, text = True, capture_output=True).stdout

    # Input and output Cotovía files
    COTOVIA_IN_TXT_PATH = res + '.txt'
    COTOVIA_IN_TXT_PATH_ISO = 'iso8859-1' + res + '.txt'
    COTOVIA_OUT_PRE_PATH = 'iso8859-1' + res + '.pre'
    COTOVIA_OUT_PRE_PATH_UTF8 = 'utf8' + res + '.pre'

    with open(COTOVIA_IN_TXT_PATH, 'w') as f:
        f.write(text + '\n')


    # utf-8 to iso8859-1
    subprocess.run(["iconv", "-f", "utf-8", "-t", "iso8859-1", COTOVIA_IN_TXT_PATH, "-o", COTOVIA_IN_TXT_PATH_ISO], stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)
    subprocess.run(["cotovia", "-i", COTOVIA_IN_TXT_PATH_ISO, "-p"], stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)
    subprocess.run(["iconv", "-f", "iso8859-1", "-t", "utf-8", COTOVIA_OUT_PRE_PATH, "-o", COTOVIA_OUT_PRE_PATH_UTF8], stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)

    segs = []
    try:
        with open(COTOVIA_OUT_PRE_PATH_UTF8, 'r') as f:
            segs = [line.rstrip() for line in f]
            # segs = [remove_tra3_tags(line) for line in segs] # modificar con punctuate_p
            segs = [punctuate_p(line) for line in segs] # modificar con punctuate_p
    except:
        print("ERROR: Couldn't read cotovia output")

    subprocess.run(["rm", COTOVIA_IN_TXT_PATH, COTOVIA_IN_TXT_PATH_ISO, COTOVIA_OUT_PRE_PATH, COTOVIA_OUT_PRE_PATH_UTF8], stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)

    return segs

def text_preprocess(text):

    cotovia_preproc_text = to_cotovia(text)

    # convert list to string
    cotovia_preproc_text_res = ' '.join(cotovia_preproc_text)
    

    # add final punctuation if missing
    if cotovia_preproc_text_res[-1] not in string.punctuation:
        cotovia_preproc_text_res += '.'

    return cotovia_preproc_text_res


def main():
    parser = argparse.ArgumentParser(description='Cotovía text normalisation')
    parser.add_argument('text', type=str, help='Text to synthetize')
    parser.add_argument('model_path', type=str, help='Absolute path to the model checkpoint.pth')
    parser.add_argument('config_path', type=str, help='Absolute path to the model config.json')

    args = parser.parse_args()

    print("Text before preprocessing: ", args.text)
    text = text_preprocess(args.text)
    print("Text after preprocessing: ", text)

    synthesizer = Synthesizer(
        args.model_path, args.config_path, None, None, None, None,
    )

    # Step 1: Extract the first word from the text
    first_word = args.text.split()[0] if args.text.split() else "audio"
    first_word = sanitize_filename(first_word)  # Sanitize to make it a valid filename

    # Step 2: Use synthesizer's built-in function to synthesize and save the audio
    wavs = synthesizer.tts(text)
    filename = f"{first_word}.wav"
    synthesizer.save_wav(wavs, filename)

    print(f"Audio file saved as: {filename}")

if __name__ == "__main__":
    main()