Hugging Face's logo

Spaces:
guymorlan
/
levanti_he_ar
Running

App Files Community
levanti_he_ar
File size: 5,097 Bytes 
46f657a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
149
150
151
152
153
154
155
156
157
158
159
 
#%%
from transformers import CanineForTokenClassification, AutoTokenizer
import re
import torch

# instantiate module logger
import logging
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)

model = CanineForTokenClassification.from_pretrained("guymorlan/levanti_diacritics2translit")
tokenizer = AutoTokenizer.from_pretrained("guymorlan/levanti_diacritics2translit")

#%%

def diacritics2hebrew_vowels(text, model, tokenizer):
    tokens = tokenizer(text, return_tensors="pt")
    with torch.no_grad():
        pred = model(**tokens)
        pred = pred.logits.argmax(-1).tolist()
        
    pred = pred[0][1:-1] # remove CLS and SEP
    output = []
    for p, c in zip(pred, text):
        if p != model.config.label2id["O"]:
            output.append(model.config.id2label[p])
        else:
            output.append(c)
    output = "".join(output)
    
    # print("Done converting to Hebrew vowels")
    logger.warning("Done converting to Hebrew vowels")
    return output

#%%


arabic_to_english = {
    "ا": "a", "أ": "a", "إ": "a", "ء": "a", "ئ": "a", "ؤ": "a",
    "آ": "aa", "ى": "a", "ب": "b", "ت": "t", "ث": "th", "ج": "j",
    "ح": "h", "خ": "kh", "د": "d", "ذ": "dh", "ر": "r", "ز": "z",
    "س": "s", "ش": "sh", "ص": "s", "ض": "d", "ط": "t", "ظ": "z",
    "ع": "a", "غ": "gh", "ف": "f", "ق": "q", "ك": "k", "ل": "l",
    "م": "m", "ن": "n", "ه": "h", "و": "w", "ي": "y", "ة": "h",
    "َ": "a", "ُ": "u", "ِ": "i",
    "،": ",",
    "ֹ": "o",  # holam
    "ַ": "a",  # patah
    "ִ": "i",  # hiriq
    "ְ": "",   # shva
    "ֻ": "u",  # kubutz
    'ֵ': "e",
    "ّ": "SHADDA"  # shadda
}

arabic_to_hebrew = {
    # regular letters
    "ا": "א", "أ": "א", "إ": "א", "ء": "א", "ئ": "א", "ؤ": "א", 
    "آ": "אא", "ى": "א", "ب": "בּ", "ت": "ת", "ث": "ת'", "ج": "ג'", 
    "ح": "ח", "خ": "ח'", "د": "ד", "ذ": "ד'", "ر": "ר", "ز": "ז", 
    "س": "ס", "ش": "ש", "ص": "צ", "ض": "צ'", "ط": "ט", "ظ": "ט'", 
    "ع": "ע", "غ": "ע'", "ف": "פ", "ق": "ק", "ك": "כּ", "ل": "ל", 
    "م": "מ", "ن": "נ", "ه": "ה", "و": "ו", "ي": "י", "ة": "ה",
    # special characters
    "،": ",", "َ": "ַ", "ُ": "ֻ", "ِ": "ִ",
    "؟": "?", "؛": ";", "ـ": "",
    # shadda to \u0598
    "ّ": "\u0598",
}

vowels = ["،", ",", "َ", "ַ", "ُ", "ֻ", "ِ", "ִ", 'ֵ']

final_letters = {
    "ن": "ן", "م": "ם", "ص": "ץ", "ض": "ץ'", "ف": "ף",
}

def reorder_hebrew_nikkud(input_string):
    # in case of 2 character letter transliteration, move the nikkud back to the first character and not the apostrophe

    # Define a dictionary for the nikkud signs
    nikkud_signs = {
        "ֹ": "o",  # holam
        "ַ": "a",  # patah
        "ִ": "i",  # hiriq
        "ְ": "",   # shva
        "ֻ": "u",  # kubutz
        "ֵ": "e",  # tsere
        "ّ": "SHADDA"  # shadda
    }
    
    # Create a regex pattern for Hebrew letter followed by apostrophe and one of the nikkud signs
    pattern = r'([\u0590-\u05FF])(\')([' + ''.join(nikkud_signs.keys()) + '])'
    replacement = r'\1\3\2'
    
    result = re.sub(pattern, replacement, input_string)
    
    return result

def reverse_holam_shadda_vav(input_string):
    # For better readability, replace (holam, shadda, ו) with (shadda, ו, holam)
    # instead of shadda we use the replacement \u0598
    pattern = r'(\u05B9)(\u0598)(\u05D5)'
    replacement = r'\2\3\1'
    result = re.sub(pattern, replacement, input_string)
    
    return result

def to_taatik(arabic):
    taatik = []
    for index, letter in enumerate(arabic):
        if (
            (index == len(arabic) - 1 or arabic[index + 1] in {" ", ".", "،"}) and 
            letter in final_letters
        ):
            taatik.append(final_letters[letter])
        elif letter not in arabic_to_hebrew:
            taatik.append(letter)
        else:
            taatik.append(arabic_to_hebrew[letter])
    reversed = reverse_holam_shadda_vav("".join(taatik))
    reordered = reorder_hebrew_nikkud(reversed)
    # print("Done converting to taatik")
    logger.warning("Done converting to taatik")
    return reordered




def to_translit(arabic):
    translit = []
    for letter in arabic:
        if letter not in arabic_to_english:
            translit.append([letter, letter])
        else:
            if arabic_to_english[letter] == "SHADDA":
                if translit[-1][0] in vowels:
                    translit[-2][1] = translit[-2][1].upper()
                else:
                    translit[-1][1] = translit[-1][1].upper()
    
            else:
                translit.append([letter, arabic_to_english[letter]])
            
    return "".join([x[1] for x in translit])


# %%

def taatik(text):
    return to_taatik(diacritics2hebrew_vowels(text, model, tokenizer))

# text = "لَازِم نِعْطِي رَشَّات وِقَائِيِّة لِلشَّجَر "
# heb_vowels = diacritics2hebrew_vowels(text, model, tokenizer)
# #%%
# to_taatik(heb_vowels)
# #%%
# to_translit(heb_vowels)
# # %%