Zambian Language Trainer Window
Curate local language datasets and trigger asynchronous machine learning training
Multilingual
Select Target Zambian Dialect to Manage & Train:
🇿🇲
Unified (All)
🇿🇲
Chibemba
🇿🇲
Chinyanja
🇿🇲
Chitonga
🇿🇲
Silozi
🇬🇧
English
🌐
Mixed/General
Local Dataset Inspector: All
25504 Records| Phrase Text | Dialect | Category Label | Source |
|---|---|---|---|
| Tupac could fuck any bitch in the world in 1996 and niggas on here crying about a pic he took FOR BITCHES | Mixed | Abusive | User Added |
| Tuna is good the rest trash RT @AyeoFool: Cans of spam RT @MsBTxo: Most struggle food HAS TO BE any meat In a can, tuna included | Mixed | Safe | User Added |
| Tryna save a hoe that don't wanna be saved nope nope nope not me | Mixed | Abusive | User Added |
| Tryna get to home like base to base to base, closet looking like planet of the bathing apes | Mixed | Safe | User Added |
| Tryna determine if she a bad bitch, but then twitter saves her http://t.co/WNBfuiuU04 | Mixed | Abusive | User Added |
| Tryna be sumbody cinnamon apple «@DarksknStruggle Now I cant trust any bitch wit pussy that taste like cinnamon apple http://t.co/hwM427BW7V | Mixed | Abusive | User Added |
| Try to take Othot drugs bitch I'm 30'd up | Mixed | Abusive | User Added |
| Try Rex's NEW water roasted tomato/potato sawdust crackers! Loaded with enough sodium as to make Lots wife look unsavory! Only 22.99 a box! | Mixed | Safe | User Added |
| Truuuuuuuuuuu facts both then niggaz is pussy nd I'll tag em both @meekmill nd cassidy r/p by my nigga let http://t.co/NhYODSpP | Mixed | Abusive | User Added |
| Truuuuuuuuue RT @kanYeBreast: but bitch u fine tho RT @SheSeauxSaditty: I've been old all my old ass life. And that's fine. | Mixed | Abusive | User Added |
| Truth is you're about as smelly as a barn bitch. | Mixed | Abusive | User Added |
| Truth is @MaxOn_MaxOff5 ate yellow snow as a child.. | Mixed | Abusive | User Added |
Add Local Phrase
Batch Import CSV
CSV OnlyUpload a custom CSV file to bulk import training data across all languages. Required columns: phrase (or text), category (0=Hate, 1=Abusive, 2=Safe), and optionally language.
Model Training Control
20%
Evaluation Results
Trained Algorithm:
Decision Tree
ACCURACY
F1 SCORE
Confusion Matrix Grid
46
0
0
2
41
4
0
0
47
Columns: Predicted
Rows: Actual
Algorithm Accuracy Graph