You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+4Lines changed: 4 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -2,6 +2,10 @@
2
2
3
3
A Simple PoC (Proof of Concept) of Hate-speech (Toxic content) Detector API Server using model from [detoxify](https://github.com/unitaryai/detoxify). Detoxify (unbiased model) achieves score of 93.74% compared to top leaderboard score with 94.73% in [Jigsaw Unintended Bias in Toxicity Classification](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification).
4
4
5
+
## Demo
6
+
7
+
A demo instance is available on [HuggingFace Spaces - https://atrifat-hate-speech-detector-api-demo.hf.space](https://atrifat-hate-speech-detector-api-demo.hf.space). There is no guarantee for the uptime, but feel free to test.
8
+
5
9
## Requirements
6
10
7
11
Python 3.9 or Python 3.10 is required to run the app. There is [bug/issue](https://github.com/unitaryai/detoxify/issues/94) for Python 3.11 or higher version affecting detoxify library.
0 commit comments