text/__init__.py

""" from https://github.com/keithito/tacotron """
import re
import pickle
import torch

from text import cleaners
from text.symbols import symbols

# Customized dictionary for label-to-feature conversion
with open('text/phoible_dict_2024.pkl', 'rb') as readfile:
	phoible_dict = pickle.load(readfile)

# Mappings from symbol to numeric ID and vice versa:
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
_id_to_symbol = {i: s for i, s in enumerate(symbols)}

# Regular expression matching text enclosed in curly braces:
_curly_re = re.compile(r"(.*?)\{(.+?)\}(.*)")


# FEATURE-INPUT VERSION
#################################################################################################
def text_to_sequence(text, cleaner_names):
    text = text.strip("{}") # input is surrounded by {} following ming024's convention
    
    # create feature sequence
    sequence = torch.zeros((45)).unsqueeze(0) # initialize with the right dimension
    stress_masks = torch.zeros(len(text.split(' '))) # stress masks (True if stressed)
    
    for index, phone in enumerate(text.split(' ')):
        try: temp = phoible_dict[phone.strip('ˈ')].unsqueeze(0) # get from feature dict (ignore stress)
        except KeyError: print(phone)
        if phone.startswith('ˈ'): # if stressed
            stress_masks[index] = True
        sequence = torch.cat((sequence, temp), 0)
    sequence = sequence[1:, :] # get rid of first index: all zeros

    sequence[:, 9] = torch.where(stress_masks == True, 1.0, 0.0) # assign stress at the same time

    return sequence
#################################################################################################

# LABEL-INPUT VERSION
#################################################################################################
# def text_to_sequence(text, cleaner_names):
#     """Converts a string of text to a sequence of IDs corresponding to the symbols in the text.

#     The text can optionally have ARPAbet sequences enclosed in curly braces embedded
#     in it. For example, "Turn left on {HH AW1 S S T AH0 N} Street."

#     Args:
#       text: string to convert to a sequence
#       cleaner_names: names of the cleaner functions to run the text through

#     Returns:
#       List of integers corresponding to the symbols in the text
#     """
#     sequence = []

#     # Check for curly braces and treat their contents as ARPAbet:
#     while len(text):
#         m = _curly_re.match(text)

#         if not m:
#             sequence += _symbols_to_sequence(_clean_text(text, cleaner_names))
#             break
#         sequence += _symbols_to_sequence(_clean_text(m.group(1), cleaner_names))
#         sequence += _arpabet_to_sequence(m.group(2))
#         text = m.group(3)

#     return sequence
#################################################################################################


def sequence_to_text(sequence):
    """Converts a sequence of IDs back to a string"""
    result = ""
    for symbol_id in sequence:
        if symbol_id in _id_to_symbol:
            s = _id_to_symbol[symbol_id]
            # Enclose ARPAbet back in curly braces:
            if len(s) > 1 and s[0] == "@":
                s = "{%s}" % s[1:]
            result += s
    return result.replace("}{", " ")


def _clean_text(text, cleaner_names):
    for name in cleaner_names:
        cleaner = getattr(cleaners, name)
        if not cleaner:
            raise Exception("Unknown cleaner: %s" % name)
        text = cleaner(text)
    return text


def _symbols_to_sequence(symbols):
    missing=[s for s in symbols if not _should_keep_symbol(s)]
    if missing:
        print('MISSING!: ', missing)
    return [_symbol_to_id[s] for s in symbols if _should_keep_symbol(s)]


def _arpabet_to_sequence(text):
    return _symbols_to_sequence(["@" + s for s in text.split()])


def _should_keep_symbol(s):
    return s in _symbol_to_id and s != "_" and s != "~"