You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello! Using the "quick_yield_single_sentence_fragment" parameter entails the separation of non-integer numbers and prices, which significantly affects the quality of the TTS:
["The price for Pure Leaf Sweet Tea is $3.", "5 for small size and $5 for large size."]
The text was updated successfully, but these errors were encountered:
Yes, true. I use the NLTK or stanza tokenizers for the standard "splitting into sentence" logic. These tokenizers can't split in comma as of my knowledge. Therefore quick_yield_single_sentence_fragment uses a very simplified splitting logic only based on detection of single characters.
Hello! Using the "quick_yield_single_sentence_fragment" parameter entails the separation of non-integer numbers and prices, which significantly affects the quality of the TTS:
["The price for Pure Leaf Sweet Tea is $3.", "5 for small size and $5 for large size."]
The text was updated successfully, but these errors were encountered: