Spaces:
Sleeping
Sleeping
File size: 2,781 Bytes
5d9390a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
"""
Copied from https://github.com/neonbjb/tortoise-tts/blob/main/tortoise/utils/text.py
"""
import re
def split_and_recombine_text(text, desired_length=1, max_length=300):
"""Split text it into chunks of a desired length trying to keep sentences intact."""
# normalize text, remove redundant whitespace and convert non-ascii quotes to ascii
text = re.sub(r'\n\n+', '\n', text)
text = re.sub(r'\s+', ' ', text)
text = re.sub(r'[“”]', '"', text)
rv = []
in_quote = False
current = ""
split_pos = []
pos = -1
end_pos = len(text) - 1
def seek(delta):
nonlocal pos, in_quote, current
is_neg = delta < 0
for _ in range(abs(delta)):
if is_neg:
pos -= 1
current = current[:-1]
else:
pos += 1
current += text[pos]
if text[pos] == '"':
in_quote = not in_quote
return text[pos]
def peek(delta):
p = pos + delta
return text[p] if p < end_pos and p >= 0 else ""
def commit():
nonlocal rv, current, split_pos
rv.append(current)
current = ""
split_pos = []
while pos < end_pos:
c = seek(1)
# do we need to force a split?
if len(current) >= max_length:
if len(split_pos) > 0 and len(current) > (desired_length / 2):
# we have at least one sentence and we are over half the desired length, seek back to the last split
d = pos - split_pos[-1]
seek(-d)
else:
# no full sentences, seek back until we are not in the middle of a word and split there
while c not in '!?.\n ' and pos > 0 and len(current) > desired_length:
c = seek(-1)
commit()
# check for sentence boundaries
elif not in_quote and (c in '!?\n' or (c == '.' and peek(1) in '\n ')):
# seek forward if we have consecutive boundary markers but still within the max length
while pos < len(text) - 1 and len(current) < max_length and peek(1) in '!?.':
c = seek(1)
split_pos.append(pos)
if len(current) >= desired_length:
commit()
# treat end of quote as a boundary if its followed by a space or newline
elif in_quote and peek(1) == '"' and peek(2) in '\n ':
seek(2)
split_pos.append(pos)
rv.append(current)
# clean up, remove lines with only whitespace or punctuation
rv = [s.strip() for s in rv]
rv = [s for s in rv if len(s) > 0 and not re.match(r'^[\s\.,;:!?]*$', s)]
return rv
|