Initial commit

matcha/text/__init__.py

@@ -0,0 +1,53 @@
+""" from https://github.com/keithito/tacotron """
+from matcha.text import cleaners
+from matcha.text.symbols import symbols
+
+# 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)}  # pylint: disable=unnecessary-comprehension
+
+
+def text_to_sequence(text, cleaner_names):
+    """Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
+    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 = []
+
+    clean_text = _clean_text(text, cleaner_names)
+    for symbol in clean_text:
+        symbol_id = _symbol_to_id[symbol]
+        sequence += [symbol_id]
+    return sequence
+
+
+def cleaned_text_to_sequence(cleaned_text):
+    """Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
+    Args:
+      text: string to convert to a sequence
+    Returns:
+      List of integers corresponding to the symbols in the text
+    """
+    sequence = [_symbol_to_id[symbol] for symbol in cleaned_text]
+    return sequence
+
+
+def sequence_to_text(sequence):
+    """Converts a sequence of IDs back to a string"""
+    result = ""
+    for symbol_id in sequence:
+        s = _id_to_symbol[symbol_id]
+        result += s
+    return result
+
+
+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

matcha/text/cleaners.py

@@ -0,0 +1,105 @@
+""" from https://github.com/keithito/tacotron
+
+Cleaners are transformations that run over the input text at both training and eval time.
+
+Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
+hyperparameter. Some cleaners are English-specific. You'll typically want to use:
+  1. "english_cleaners" for English text
+  2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
+     the Unidecode library (https://pypi.python.org/pypi/Unidecode)
+  3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
+     the symbols in symbols.py to match your data).
+"""
+
+import logging
+import re
+
+import phonemizer
+from unidecode import unidecode
+
+# To avoid excessive logging we set the log level of the phonemizer package to Critical
+critical_logger = logging.getLogger("phonemizer")
+critical_logger.setLevel(logging.CRITICAL)
+
+# Intializing the phonemizer globally significantly reduces the speed
+# now the phonemizer is not initialising at every call
+# Might be less flexible, but it is much-much faster
+global_phonemizer = phonemizer.backend.EspeakBackend(
+    language="en-us",
+    preserve_punctuation=True,
+    with_stress=True,
+    language_switch="remove-flags",
+    logger=critical_logger,
+)
+
+
+# Regular expression matching whitespace:
+_whitespace_re = re.compile(r"\s+")
+
+# List of (regular expression, replacement) pairs for abbreviations:
+_abbreviations = [
+    (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+    for x in [
+        ("mrs", "misess"),
+        ("mr", "mister"),
+        ("dr", "doctor"),
+        ("st", "saint"),
+        ("co", "company"),
+        ("jr", "junior"),
+        ("maj", "major"),
+        ("gen", "general"),
+        ("drs", "doctors"),
+        ("rev", "reverend"),
+        ("lt", "lieutenant"),
+        ("hon", "honorable"),
+        ("sgt", "sergeant"),
+        ("capt", "captain"),
+        ("esq", "esquire"),
+        ("ltd", "limited"),
+        ("col", "colonel"),
+        ("ft", "fort"),
+    ]
+]
+
+
+def expand_abbreviations(text):
+    for regex, replacement in _abbreviations:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def lowercase(text):
+    return text.lower()
+
+
+def collapse_whitespace(text):
+    return re.sub(_whitespace_re, " ", text)
+
+
+def convert_to_ascii(text):
+    return unidecode(text)
+
+
+def basic_cleaners(text):
+    """Basic pipeline that lowercases and collapses whitespace without transliteration."""
+    text = lowercase(text)
+    text = collapse_whitespace(text)
+    return text
+
+
+def transliteration_cleaners(text):
+    """Pipeline for non-English text that transliterates to ASCII."""
+    text = convert_to_ascii(text)
+    text = lowercase(text)
+    text = collapse_whitespace(text)
+    return text
+
+
+def english_cleaners2(text):
+    """Pipeline for English text, including abbreviation expansion. + punctuation + stress"""
+    text = convert_to_ascii(text)
+    text = lowercase(text)
+    text = expand_abbreviations(text)
+    phonemes = global_phonemizer.phonemize([text], strip=True, njobs=1)[0]
+    phonemes = collapse_whitespace(phonemes)
+    return phonemes

matcha/text/numbers.py

@@ -0,0 +1,71 @@
+""" from https://github.com/keithito/tacotron """
+
+import re
+
+import inflect
+
+_inflect = inflect.engine()
+_comma_number_re = re.compile(r"([0-9][0-9\,]+[0-9])")
+_decimal_number_re = re.compile(r"([0-9]+\.[0-9]+)")
+_pounds_re = re.compile(r"£([0-9\,]*[0-9]+)")
+_dollars_re = re.compile(r"\$([0-9\.\,]*[0-9]+)")
+_ordinal_re = re.compile(r"[0-9]+(st|nd|rd|th)")
+_number_re = re.compile(r"[0-9]+")
+
+
+def _remove_commas(m):
+    return m.group(1).replace(",", "")
+
+
+def _expand_decimal_point(m):
+    return m.group(1).replace(".", " point ")
+
+
+def _expand_dollars(m):
+    match = m.group(1)
+    parts = match.split(".")
+    if len(parts) > 2:
+        return match + " dollars"
+    dollars = int(parts[0]) if parts[0] else 0
+    cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
+    if dollars and cents:
+        dollar_unit = "dollar" if dollars == 1 else "dollars"
+        cent_unit = "cent" if cents == 1 else "cents"
+        return f"{dollars} {dollar_unit}, {cents} {cent_unit}"
+    elif dollars:
+        dollar_unit = "dollar" if dollars == 1 else "dollars"
+        return f"{dollars} {dollar_unit}"
+    elif cents:
+        cent_unit = "cent" if cents == 1 else "cents"
+        return f"{cents} {cent_unit}"
+    else:
+        return "zero dollars"
+
+
+def _expand_ordinal(m):
+    return _inflect.number_to_words(m.group(0))
+
+
+def _expand_number(m):
+    num = int(m.group(0))
+    if num > 1000 and num < 3000:
+        if num == 2000:
+            return "two thousand"
+        elif num > 2000 and num < 2010:
+            return "two thousand " + _inflect.number_to_words(num % 100)
+        elif num % 100 == 0:
+            return _inflect.number_to_words(num // 100) + " hundred"
+        else:
+            return _inflect.number_to_words(num, andword="", zero="oh", group=2).replace(", ", " ")
+    else:
+        return _inflect.number_to_words(num, andword="")
+
+
+def normalize_numbers(text):
+    text = re.sub(_comma_number_re, _remove_commas, text)
+    text = re.sub(_pounds_re, r"\1 pounds", text)
+    text = re.sub(_dollars_re, _expand_dollars, text)
+    text = re.sub(_decimal_number_re, _expand_decimal_point, text)
+    text = re.sub(_ordinal_re, _expand_ordinal, text)
+    text = re.sub(_number_re, _expand_number, text)
+    return text

matcha/text/symbols.py

@@ -0,0 +1,17 @@
+""" from https://github.com/keithito/tacotron
+
+Defines the set of symbols used in text input to the model.
+"""
+_pad = "_"
+_punctuation = ';:,.!?¡¿—…"«»“” '
+_letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+_letters_ipa = (
+    "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
+)
+
+
+# Export all symbols:
+symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)
+
+# Special symbol ids
+SPACE_ID = symbols.index(" ")