Files
openedai-speech/pre_process_map.yaml
matatonic e4d001da93 initial
2023-11-26 21:41:59 -05:00

40 lines
704 B
YAML

# regex pairs to clean the text before speaking
- - ([^.])\.$
- \1
- - '&'
- '&'
- - '<'
- <
- - '&gt;'
- '>'
- - '&quot;'
- '"'
- - '&#x27;'
- ''''
- - '&copy;'
- '©'
- - '&reg;'
- '®'
- - '&nbsp;'
- ' '
- - '"'
- ''
- - ' biases '
- ' bias''s '
- - ex\.
- for example
- - e\.g\.
- for example
- - ' ESG '
- ' E.S.G. '
- - ' FY '
- ' F.Y. '
- - ([0-9]+)-([0-9]+)
- \1 to \2
- - '[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F700-\U0001F77F\U0001F780-\U0001F7FF\U0001F800-\U0001F8FF\U0001F900-\U0001F9FF\U0001FA00-\U0001FA6F\U0001FA70-\U0001FAFF\U00002702-\U000027B0\U000024C2-\U0001F251]+'
- ''
- - '\*\*\*'
- '*'
- - '\*\*'
- '*'