Initial commit (move files)

text/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2017 Keith Ito
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

text/__init__.py

@@ -0,0 +1,100 @@
+""" from https://github.com/keithito/tacotron """
+from text import cleaners
+from text.symbols import symbols
+import re
+
+
+# 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"(.*?)\{(.+?)\}(.*)")
+
+
+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 cleaned_text_to_sequence(cleaned_text):
+    """Converts a cleaned 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(cleaned_text):
+        m = _curly_re.match(cleaned_text)
+
+        if not m:
+            sequence += _symbols_to_sequence(cleaned_text)
+            break
+        sequence += _symbols_to_sequence(m.group(1))
+        sequence += _arpabet_to_sequence(m.group(2))
+        cleaned_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:
+    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
+
+
+def _symbols_to_sequence(symbols):
+    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 is not '_' and s is not '~'

text/arpa.py

@@ -0,0 +1,63 @@
+from g2p_en import G2p
+import gdown
+import os
+
+class ARPAPhonemizer():
+    def __init__(self, dict_override = ""):
+        dict_fn = "zdict.txt" if not len(dict_override) else dict_override
+        
+        if not len(dict_override) and not os.path.isfile(dict_fn):
+            print("Downloading ARPA dict..")
+            gdown.download("https://drive.google.com/file/d/1lYKcml_bkTiOke2TMF3F_fn7UWTYHNWp/view?usp=share_link", dict_fn, fuzzy=True, quiet=False)
+        
+        self.arpa_dict = self._load_dict(dict_fn)
+        self.g2p = G2p()
+
+    
+    def _load_dict(self, in_dpath):
+      dict_ret = {}
+
+      with open(in_dpath,encoding="utf-8-sig") as f:
+        d_lines = f.readlines()
+
+      last_word = ""
+      for d_li in d_lines:
+        splits = d_li.strip().split("\t")
+
+        word = splits[0]
+        pron = splits[1]
+
+        #only accept 1st entry for each word
+        if word == last_word:
+          continue
+
+        dict_ret[word] = pron
+        last_word = word
+
+      return dict_ret
+
+    def _g2pfil(self, intxt):
+      sta = self.g2p(intxt)
+      ret = " ".join(sta)
+      return ret
+    
+    def doARPA(self, text):
+        if text[0] == '{':
+          return text
+        out = ''
+        for word_ in text.split(" "):
+            word=word_; end_chars = ''
+            while any(elem in word for elem in r"!?,.;") and len(word) > 1:
+                if word[-1] == '!': end_chars = '!' + end_chars; word = word[:-1]
+                if word[-1] == '?': end_chars = '?' + end_chars; word = word[:-1]
+                if word[-1] == ',': end_chars = ',' + end_chars; word = word[:-1]
+                if word[-1] == '.': end_chars = '.' + end_chars; word = word[:-1]
+                if word[-1] == ';': end_chars = ';' + end_chars; word = word[:-1]
+                else: break
+            try: word_arpa = self.arpa_dict[word.lower()]
+            except: word_arpa = self._g2pfil(word)
+            if len(word_arpa)!=0: word = "{" + str(word_arpa) + "}"
+            out = (out + " " + word + end_chars).strip()
+
+        return out
+

text/cleaners.py

@@ -0,0 +1,146 @@
+""" 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 re
+from unidecode import unidecode
+from phonemizer import phonemize
+import phonemizer
+from .arpa import ARPAPhonemizer
+
+global_phonemizer = phonemizer.backend.EspeakBackend(language='en-us', preserve_punctuation=True,  with_stress=True)
+spanish_phonemizer = phonemizer.backend.EspeakBackend(language='es-419', preserve_punctuation=True,  with_stress=True)
+
+fest_phonemizer = phonemizer.backend.FestivalBackend(language='en-us', preserve_punctuation=True)
+arpa_phonemizer = ARPAPhonemizer()
+
+
+
+
+# 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 expand_numbers(text):
+  return normalize_numbers(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_cleaners(text):
+  '''Pipeline for English text, including abbreviation expansion.'''
+  text = convert_to_ascii(text)
+  text = lowercase(text)
+  text = expand_abbreviations(text)
+  phonemes = phonemize(text, language='en-us', backend='espeak', strip=True)
+  phonemes = collapse_whitespace(phonemes)
+  return phonemes
+
+
+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)
+  phonemes = phonemes[0]
+  phonemes = collapse_whitespace(phonemes)
+  return phonemes
+
+def f_english_cleaners2(text):
+  '''Pipeline for English text with Festival phonemizer, including abbreviation expansion. + punctuation'''
+  text = convert_to_ascii(text)
+  text = lowercase(text)
+  text = expand_abbreviations(text)
+  phonemes = fest_phonemizer.phonemize([text], strip=True, njobs=1)
+  phonemes = phonemes[0]
+  phonemes = collapse_whitespace(phonemes)
+  return phonemes
+
+def arpa_precleaners(text):
+  '''Pipeline for English text before ARPA'''
+  text = convert_to_ascii(text)
+  text = lowercase(text)
+  text = expand_abbreviations(text)
+
+  return text
+
+def arpa_cleaners(text):
+  '''Pipeline for ARPA English text, including abbreviation expansion. + punctuation + stress'''
+  text = convert_to_ascii(text)
+  text = lowercase(text)
+  text = expand_abbreviations(text)
+  phonemes = arpa_phonemizer.doARPA(text)
+
+  return phonemes
+
+def spanish_cleaners(text):
+  '''Pipeline for Spanish text, punctuation + stress'''
+  text = lowercase(text)
+  phonemes = spanish_phonemizer.phonemize([text], strip=True, njobs=1)
+  phonemes = phonemes[0].replace("(es-419)","").replace("(en)","")
+  phonemes = collapse_whitespace(phonemes)
+  return phonemes

text/symbols.py

@@ -0,0 +1,22 @@
+""" from https://github.com/keithito/tacotron """
+
+'''
+Defines the set of symbols used in text input to the model.
+'''
+from g2p_en import g2p as grapheme_to_phonem
+g2p = grapheme_to_phonem.G2p()
+
+_pad        = '_'
+_punctuation = ';:,.!?¡¿—…"«»“” '
+_letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
+_letters_ipa = "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
+arpa_sym = g2p.phonemes
+_arpabet = ["@" + s for s in arpa_sym]
+
+
+
+# Export all symbols:
+symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa) + _arpabet
+
+# Special symbol ids
+SPACE_ID = symbols.index(" ")