Hossep Dolatian

Hiya. Hmm. So I tried to make it easier for myself by trying to convert my text files into an excel sheet that's organized by book-chapter-verse. Because I had already...

sure @christos-c. [Here](https://file.io/IfjG44LmKWki) is a bit of Genesis. The first row (the headers) is pretty intuitive (book, chapter #, verse #, the actual content)

Thanks @christos-c. It did work ([here](https://drive.google.com/file/d/1QGu_cG-wb6SjwPwW_yLPDTL9pOM9ArKu/view?usp=sharing)). A minor issue is that I had manually compiled the original TSV a year or so ago by copying from a liturgical website. The...

@christos-c they would replace them because they're three iso-codes and they're complete.

I managed to get the Armenian Wiktionary editors to upgrade their script so that the colloquial entries now have a more informative text, like Portuguese.

Well for Armenian, most of the [entries](https://en.wiktionary.org/wiki/%D5%A5%D6%80%D5%AF%D6%80%D5%B8%D6%80%D5%A4) now look like Portuguese. There are still probably some stragglers because of some older entries. But I can find+fix those once I find...

A possible cheat is that you extract only the URL of the audio file (that I think is hosted on some Wiki domain). Then you can suggest in the README...

It's understandable that you shouldn't do much hermeneutics. And ideally it should be a thing that the Wiktionary entries themselves should fix. But I don't think it'll be changed any...

Hi. The readme recommends the use of the flag --no-skip-parens. I used pip (and pip3) right now to get wikipron. But the argument --no-skip-parens is not recognized ``` usage: wikipron...

To piggyback off of this bug, I tried running `--uses_speaker_adaptation False` but it seemed to still do speaker adaptation. ``` ~ % mfa train --clean AUDIO_DIRECTORY DICTIONARY.xt MODEL.zip OUTPUT_DIRECTORY --beam=100...