-
I'm not really sure how to explain this, but when reading Japanese VN's sometimes there is a "text over text" thing (not sure how to call it), I'm talking about this:
![03mod](https://user-images.g…
-
**Description**: Write a function to split the generated text into words and check each word against the English word list to determine its validity.
**Checklist**:
- [ ] Research methods for tok…
-
Currently, this library splits the text exactly at the 100 character mark to comply with Google TTS character limit. I think it's better if it cuts off at the last whitespace near the 100 character ma…
-
Inspiration: 5-levels of chunking
[https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb](https://github.com/FullSt…
-
As title says.
When you split a subtitle (in Spectrogram) it splits the text in the selected subtitle as well.
Would love to know if it is possible to make the subtitles not split as an option
Th…
-
Just got the following error, seems to be hitting the limit in coqui TTS.
```
Chapter 50: 20%|████████████▌ | 1/5 [10:51
-
Noticed that when splitting by character, it splits words onto a new line mid-way, so a long word like:
characteristics
becomes:
characte
ristics
... if there's no room on the line the te…
-
**Is your feature request related to a problem? Please describe.**
Currently the `DocumentSplitter` in Haystack is relatively basic and recently we have seen that semantic splitting has greatly gaine…
-
**Describe the issue**
While playing at non-wide resolutions vanilla(non-sdf fonts) can be too large to fit on the screen, usually when using mods
**To Reproduce**
1. Disable sdf fonts
2. Tr…
-
Currently, markdown gets messed up when very long messages are split. We need to implement something to preserve the formatting between split messages