def normalize_string(s, labels, table, **unused_kwargs):
"""
Normalizes string. For example:
'call me at 8:00 pm!' -> 'call me at eight zero pm'
Args:
s: string to normalize
labels: labels used during model training.
Returns:
Normalized string
"""
def good_token(token, labels):
s = set(labels)
for t in token:
if not t in s:
return False
return True
try:
text = _clean_text(s, ["english_cleaners"], table).strip()
return ''.join([t for t in text if good_token(t, labels=labels)])
except:
print("WARNING: Normalizing {} failed".format(s))
return None
def normalize_string(s, symbols, punct_map):
"""
Normalizes string.
Example:
'call me at 8:00 pm!' -> 'call me at eight zero pm'
"""
labels = set(symbols)
try:
text = _clean_text(s, ["english_cleaners"], punct_map).strip()
return ''.join([tok for tok in text if all(t in labels for t in tok)])
except Exception as e:
print_once("WARNING: Normalizing failed: {s} {e}")
def normalize_string(s, charset, punct_map):
"""Normalizes string.
Example:
'call me at 8:00 pm!' -> 'call me at eight zero pm'
"""
charset = set(charset)
try:
text = _clean_text(s, ["english_cleaners"], punct_map).strip()
return ''.join([tok for tok in text if all(t in charset for t in tok)])
except:
print(f"WARNING: Normalizing failed: {s}")
return None