AniMAntZeZo commited on
Commit
a2c73cf
·
verified ·
1 Parent(s): 16e168a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -10,7 +10,6 @@ pipeline_tag: text-classification
10
  ---
11
 
12
  # RuBert-tiny2-EmotionsDetected
13
- # RuBert-tyny2-EmotionsDetected
14
 
15
  This model was obtained by fine-tuning the model [RuBert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the dataset [ru-goemotions](https://github.com/searayeah/ru-goemotions) containing 28 emotions:
16
  ```
@@ -55,4 +54,16 @@ At the moment, the model has been trained for 40 epochs with the following hyper
55
  load_best_model_at_end=True,
56
  metric_for_best_model="f1",
57
  greater_is_better=True
58
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  # RuBert-tiny2-EmotionsDetected
 
13
 
14
  This model was obtained by fine-tuning the model [RuBert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the dataset [ru-goemotions](https://github.com/searayeah/ru-goemotions) containing 28 emotions:
15
  ```
 
54
  load_best_model_at_end=True,
55
  metric_for_best_model="f1",
56
  greater_is_better=True
57
+ ```
58
+
59
+ ## Test
60
+ With the help of a well-known AI, a data set was compiled to verify the veracity of the model's predictions. Here's what happened:
61
+ **!The data for the test did not undergo a thorough manual inspection!**
62
+
63
+ ![TrueEmotion](https://huggingface.co/AniMAntZeZo/RuBert-tiny2-EmotionsDetected/blob/main/RuBert-tiny2-EmotionsDetected/img/TrueEmotion.png)
64
+ ![PredictedEmotion](https://huggingface.co/AniMAntZeZo/RuBert-tiny2-EmotionsDetected/blob/main/RuBert-tiny2-EmotionsDetected/img/PredictedEmotion.png)
65
+ ![Comparison](https://huggingface.co/AniMAntZeZo/RuBert-tiny2-EmotionsDetected/blob/main/RuBert-tiny2-EmotionsDetected/img/Comparison.png)
66
+
67
+ It can be seen from the above that the model is able to distinguish between basic emotions, but has problems with specific ones (grief (горе), pride (гордость)), and also defines a neutral emotion more often than expected (most likely this happened due to inaccuracies in the dataset, since in ordinary speech you can "use" several emojis at once and most often people use the neutral one)
68
+
69
+ The model will be updated as improvements are made.