|
""" from https://github.com/keithito/tacotron """ |
|
from text import cleaners |
|
from text.symbols import symbols |
|
from text import cleaners1 |
|
from text.symbols1 import symbols1 |
|
|
|
|
|
_symbol_to_id = {s: i for i, s in enumerate(symbols)} |
|
_id_to_symbol = {i: s for i, s in enumerate(symbols)} |
|
_symbol_to_id1 = {s: i for i, s in enumerate(symbols1)} |
|
_id_to_symbol1 = {i: s for i, s in enumerate(symbols1)} |
|
|
|
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) |
|
return cleaned_text_to_sequence(clean_text) |
|
|
|
|
|
def text_to_sequence1(text, cleaner_names): |
|
sequence = [] |
|
clean_text = _clean_text1(text, cleaner_names) |
|
return cleaned_text_to_sequence1(clean_text) |
|
|
|
|
|
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 = [] |
|
for symbol in cleaned_text.split(" "): |
|
if symbol in _symbol_to_id: |
|
sequence.append(_symbol_to_id[symbol]) |
|
else: |
|
for s in symbol: |
|
sequence.append(_symbol_to_id[s]) |
|
sequence.append(_symbol_to_id[" "]) |
|
if sequence[-1] == _symbol_to_id[" "]: |
|
sequence = sequence[:-1] |
|
return sequence |
|
|
|
def cleaned_text_to_sequence1(cleaned_text): |
|
sequence = [] |
|
for symbol1 in cleaned_text.split(" "): |
|
if symbol1 in _symbol_to_id1: |
|
sequence.append(_symbol_to_id1[symbol1]) |
|
else: |
|
for s in symbol1: |
|
sequence.append(_symbol_to_id1[s]) |
|
sequence.append(_symbol_to_id1[" "]) |
|
if sequence[-1] == _symbol_to_id1[" "]: |
|
sequence = sequence[:-1] |
|
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 _clean_text1(text, cleaner_names): |
|
for name in cleaner_names: |
|
cleaner = getattr(cleaners1, name) |
|
if not cleaner: |
|
raise Exception('Unknown cleaner: %s' % name) |
|
text = cleaner(text) |
|
return text |
|
|
