-
- [ ] Dundul Dorje
- [ ] "chokyi dronma" in phonetics, finding unrelated stuff:
![Capture d’écran de 2024-10-29 16-03-42](https://github.com/user-attachments/assets/bb418b20-4779-4f4a-b101-d4f1f08…
-
Now that we've decided on the phonetics route, there are a few things to consider:
The first fundamental question for me is to choose between two routes:
- the first route is to create a sort of s…
eroux updated
2 months ago
-
```
[
("Jampeyang Ngawang Legdrub", "'jam pa'i dbyangs ngag dbang legs grub"),
("Atiśa Dīpaṃkara", "a ti sha dI paM ka ra"),
("Bari Lotsāwa", "ba ri lo tsA ba rin chen grags"),
…
-
let's implement a very simple phonetic analyzer, it would have two functions (a bit like the Sanskrit lenient analyzer):
- convert Tibetan into phonetics (one token per syllable)
- convert phonetic…
eroux updated
2 months ago
-
[Phonetics Mohammad.pdf](https://github.com/user-attachments/files/17584910/Phonetics.Mohammad.pdf)
-
Excellent work on this library! Next step is ignoring malformed syllables, any tips on how to implement this?
Cheers.
-
Currently, all tokenisers work on a character level. This means that transferring them to a new language is often not possible. At the same time, this means that a model trained with such a tokeniser …
-
The rules for KVP currently implemented are outdated and need to be updated with the following document:
[KVP-phon.pdf](https://github.com/user-attachments/files/16976858/KVP-phon.pdf)
See also …
eroux updated
1 month ago
-
It would be nice to include the phonetic pronunciation within the popup, e.g.:
```
sup·port 🔊
/səˈpôrt/
Bear all or part of the weight of; hold up.
```
Great job!
-
In the new シュワー entry, which has been given the [ling] field tag, someone has suggested we have a tag for phonetics as well. I see GG5 has tags of 【言】, 【文法】 and 【言】 (e.g. on 類音), so it may be worth co…