util.py

import random
from umsc import UgMultiScriptConverter
import string
import epitran
from difflib import SequenceMatcher

# Lists of Uyghur short and long texts
short_texts = [
    "سالام", "رەھمەت", "ياخشىمۇسىز", "خۇش كېپسىز", "خەيرلىك كۈن", "خەير خوش"
]
long_texts = [
    "مەكتەپكە بارغاندا تېخىمۇ بىلىملىك بولۇمەن.",
    "يېزا مەنزىرىسى ھەقىقەتەن گۈزەل.",
    "بىزنىڭ ئۆيدە تۆت تەكچە، تۆتىلىسى تەك-تەكچە", 
    "تۆۋەندە ئالىمنىڭ تەرجىمىھالى بىلەن تونۇشۇپ ئۆتەيلى.",
    "شېئىردىكى تۇيغۇ ئورنىنى تاپالمىغان ئىستىلىستىكىلىق ۋاسىتە كۆزگە چېلىقمايدۇ."
]

# Front-End Utils
ug_arab_to_latn = UgMultiScriptConverter('UAS', 'ULS')
def generate_short_text(script_choice):
    """Generate a random Uyghur short text based on the type."""
    text = random.choice(short_texts)
    return ug_arab_to_latn(text) if script_choice == "Uyghur Latin" else text

def generate_long_text(script_choice):
    """Generate a random Uyghur long text based on the type."""
    text = random.choice(long_texts)
    return ug_arab_to_latn(text) if script_choice == "Uyghur Latin" else text

# ASR Utils
# def load_and_resample_audio(audio_data, target_rate):
#     """Load audio and resample based on target sample rate"""
#     if isinstance(audio_data, tuple):
#         # microphone
#         sampling_rate, audio_input = audio_data
#         audio_input = (audio_input / 32768.0).astype(np.float32)
#     elif isinstance(audio_data, str):
#         # file upload
#         audio_input, sampling_rate = torchaudio.load(audio_data)
#     else: 
#         return "<<ERROR: Invalid Audio Input Instance: {}>>".format(type(audio_data))
#     # Resample if needed
#     if sampling_rate != target_rate:
#         resampler = torchaudio.transforms.Resample(sampling_rate, target_rate)
#         audio_input = resampler(audio_input)

#     return audio_input, target_rate

def calculate_pronunciation_accuracy(reference_text, output_text, language_code='uig-Arab'):
    """
    Calculate pronunciation accuracy between reference and ASR output text using Epitran.

    Args:
        reference_text (str): The ground truth text in Uyghur (Arabic script).
        output_text (str): The ASR output text in Uyghur (Arabic script).
        language_code (str): Epitran language code (default is 'uig-Arab' for Uyghur).

    Returns:
        float: Pronunciation accuracy as a percentage.
        str: IPA transliteration of the reference text.
        str: IPA transliteration of the output text.
    """
    # Initialize Epitran for Uyghur (Arabic script)
    ipa_converter = epitran.Epitran(language_code)

    # Remove punctuation from both texts
    reference_text_clean = remove_punctuation(reference_text)
    output_text_clean = remove_punctuation(output_text)

    # Transliterate both texts to IPA
    reference_ipa = ipa_converter.transliterate(reference_text_clean)
    output_ipa = ipa_converter.transliterate(output_text_clean)

    # Calculate pronunciation accuracy using SequenceMatcher
    matcher = SequenceMatcher(None, reference_text_clean, output_text_clean)
    match_ratio = matcher.ratio()  # This is the fraction of matching characters

    # Convert to percentage
    pronunciation_accuracy = match_ratio * 100

    # Generate Markdown-compatible styled text
    comparison_md = ""
    for opcode, i1, i2, j1, j2 in matcher.get_opcodes():
        ref_segment = reference_text_clean[i1:i2]
        out_segment = output_text_clean[j1:j2]

        if opcode == 'equal':  # Matching characters
            comparison_md += f'<span style="color: blue;">{ref_segment}</span>'
        elif opcode in ['replace', 'delete', 'insert']:  # Mismatched or missing
            comparison_md += f'<span style="color: black;">{ref_segment}</span>'

    comparison_md = f"<div>{comparison_md}</div>"

    return reference_ipa, output_ipa, comparison_md, pronunciation_accuracy

def remove_punctuation(text):
  """Helper function to remove punctuation from text."""
  return text.translate(str.maketrans('', '', string.punctuation))