MycroftAI
/
mimic2
mirror of https://github.com/MycroftAI/mimic2.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Clean up

pull/2/head
Keith Ito 2017-09-04 21:37:58 -07:00
parent c724ac2f4c
commit 9e1ea7a879
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
text/__init__.py
View File

@ -12,7 +12,7 @@ _curly_re = re.compile(r'(.*?)\{(.+?)\}(.*)')
def text_to_sequence(text, cleaner_names):
'''Converts a string of text to a sequence of IDs for the symbols in the text.
'''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."
@ -30,9 +30,9 @@ def text_to_sequence(text, cleaner_names):
while len(text):
m = _curly_re.match(text)
if not m:
sequence += _characters_to_sequence(_clean_text(text, cleaner_names))
sequence += _symbols_to_sequence(_clean_text(text, cleaner_names))
break
sequence += _characters_to_sequence(_clean_text(m.group(1), cleaner_names))
sequence += _symbols_to_sequence(_clean_text(m.group(1), cleaner_names))
sequence += _arpabet_to_sequence(m.group(2))
text = m.group(3)
@ -63,13 +63,12 @@ def _clean_text(text, cleaner_names):
return text
def _characters_to_sequence(chars):
return [_symbol_to_id[s] for s in chars if _should_keep_symbol(s)]
def _symbols_to_sequence(symbols):
return [_symbol_to_id[s] for s in symbols if _should_keep_symbol(s)]
def _arpabet_to_sequence(text):
arpabet_symbols = ['@' + s for s in text.split()]
return [_symbol_to_id[s] for s in arpabet_symbols if _should_keep_symbol(s)]
return _symbols_to_sequence(['@' + s for s in text.split()])
def _should_keep_symbol(s):