gilleti commited on
Commit
aca7b51
·
1 Parent(s): d864c94

included swedish examples

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -20,7 +20,7 @@ Accuracy on a number of experiments on a minimal test set (35 examples) can be f
20
 
21
  ![plot](./emotional_accuracy.svg)
22
 
23
- Please note that these results are not a good representation of the model's actual performance. As previously stated, the test set is tiny and the examples in that test set are cherry picked. This model will be properly evaluated on real life data at a later time.
24
 
25
  Id to emotional label schema is as follows:
26
 
@@ -53,9 +53,11 @@ from setfit import SetFitModel
53
  # Download from Hub and run inference
54
  model = SetFitModel.from_pretrained("gilleti/emotional-classification")
55
  # Run inference
56
- preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
57
  ```
58
 
 
 
59
  ## BibTeX entry and citation info
60
 
61
  ```bibtex
 
20
 
21
  ![plot](./emotional_accuracy.svg)
22
 
23
+ Please note that these results are not a good representation of the model's actual performance. As previously stated, the test set is tiny and the examples in that test set are chosen to be good examples of the categories at hand. This is not the case with real life data. The model will be properly evaluated on real data at a later time.
24
 
25
  Id to emotional label schema is as follows:
26
 
 
53
  # Download from Hub and run inference
54
  model = SetFitModel.from_pretrained("gilleti/emotional-classification")
55
  # Run inference
56
+ preds = model(["Ingen tech-dystopi slår människans inre mörker", "Ina Lundström: Jag har två Bruce-tatueringar"])
57
  ```
58
 
59
+ This outputs predictions sadness/disappointment and absence of emotion. Please note that these examples are cherrypicked as most headlines (which is what the model is trained on) are rarely clear.
60
+
61
  ## BibTeX entry and citation info
62
 
63
  ```bibtex