translit.py

#%%
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": "ā", "أ": "ʔ", "إ": "a", "ء": "a", "ئ": "a", "ؤ": "a",
    "آ": "aa", "ى": "a", "ب": "b", "ت": "t", "ث": "th", "ج": "j",
    "ح": "ḥ", "خ": "kh", "د": "d", "ذ": "dh", "ر": "r", "ز": "z",
    "س": "s", "ش": "š", "ص": "s", "ض": "d", "ط": "t", "ظ": "z",
    "ع": "ʕ", "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))

def translit(text):
    return to_translit(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)
# # %%