-
Hey folks.
Thanks for all the effort you've put into this problem so far. After discovering whisper's poor WER rate for Indic languages, a deep dive brought me here.
Now ideally I could load this …
-
To make progress on Indic shaping we've assembled a corpus of words and syllables by scraping Wikipedia for the ten Indic languages we plan to support (hi.wikipedia.org, bn.wikipedia.org, etc.)
Tha…
-
Our text rendering strategy cuts corners to achieve maximal performance in a web-based environment. We render glyphs to a texture atlas and then composite them on the GPU with a texture-mapped quad re…
-
When `Unicode::CaseOptions::ASCII` is passed to a method like `#downcase`, the `Unicode::CaseOptions::Turkic` pairs `I → ı` and `i → İ` are ignored for a good reason: an ASCII input string must remain…
-
### Issue
Most of the modern filesystem, including ext3 and ext4, has a file / folder name limit which is 255 bytes or we can say 255 ANSI characters. If anyone use data encryption (mostly eCryptfs, …
-
As the second recipe after NLLB, write the w2v-BERT (and wav2vec2) pretraining recipe for users to check out. This will likely branch to several subtasks once we start working on it.
-
This is a 2 parter:
1. In settings, add ability to change language from the default language chosen by react-native-localization.
2. If India is the detected country or hindi the detected langua…
-
I have recently started using the ITRANS Romanisation keyboard but I realise that there is a need of a few more extra characters to correctly phonetically type quite a few Indic languages… These addit…
-
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
when selecting an indic input method…
-
**Bengali font if in lyrics is not rendered properly**
The [Yuktakshars](https://www.aczoom.com/itrans/html/beng/node5.html) are not being rendered properly as expected.
For example the first ma…