Orthography
After a quick look, I think the characters ɛ, ɣ, ŋ, ɔ, ʒ are being processed correctly, which is good.

Stopwords
We've started working on a stopword list, including the candidates below.

• nyini, ŋuna, ba , mma , viɛlim

I've also put together a list of words from Dagbani Wikipedia sorted by frequency, for review.

Frequency list notes:

• I got about 12,000 words from Dagbani Wikipedia articles and did some minor cleanup on them. These are all the words that appeared 3 times or more from that list. There's obviously some English words and some names (Dagbaŋ, Ghana), but a quick look in a Dagbani/English dictionary shows that the top of the list has some good candidates!

A few things to keep in mind when reviewing the list:

• you don't have to look at the whole list! Start at the top and work your way down, as long as it seems productive
• feel free to add variations on words that aren't present, or any that are similar. For example, in English, seeing "a" might make you think to add "an"; seeing "of" might make you think to add "to", "from", "for", etc.
• some words are sometimes stop words and sometimes not, like "can" in English; if it is usually a stop word, include it in the stop word list; if it is usually not a stop word, don't
• stop words are not completely ignored, but they are heavily discounted
• a pretty good list of stop words is very helpful; it doesn't have to be perfect, and it is relatively easy to remove words if they cause problems

Thank you so much for initiating this TJones. Looking forward to the outcome.