Update README.md

README.md

@@ -10,9 +10,11 @@ pipeline_tag: text-classification
 # Sentiment Analysis Model
 ### This model is used in our transcription service, where the audio is first transcribed and then analysed via this model.
 
-The model expects a sentence and return a number from 1 to 5 where 1 is the most negative sentiment and 5 is the most positive one.
+The model expects a sentence and return a number from 1 to 5 where 1 is the most negative sentiment and 5 is the most positive one. There is a parsing present that checks the confidence and if it is below 0.7, it checks for the second most probable result, averages them and uses math.ceil for optimistic behavior.
 
-The model is trained on BERT (nlptown/bert-base-multilingual-uncased-sentiment), which has an MIT license, and distilled llm results
+The model is trained on BERT (nlptown/bert-base-multilingual-uncased-sentiment), which has an MIT license, and distilled llm results (./sentiment.txt)
+
+Currently the last, and most accurate model is sentiment_model_6_1
 
 This model was trained for 20 epochs where the result is:
 
@@ -28,8 +30,9 @@ This model was trained for 20 epochs where the result is:
 | **Macro avg**| 0.84      | 0.82   | 0.83     | 230     |
 | **Weighted avg** | 0.83  | 0.83   | 0.83     | 230     |
 
-## History:
-| Version | Changelog                                                       |
-|---------|-----------------------------------------------------------------|
-| **1.0** | initial training                                                |
-| **1.1** | fine-tuning time and datetime to a neutral sentiment (2 epochs) |
+## sentiment_model_6:
+| Version | Changelog                                            |
+|---------|------------------------------------------------------|
+| **1.0** | initial training                                     |
+| **1.1** | fine-tuning time and datetime to a neutral sentiment |
+| **1.2** | fine-tuning numbers to a neutral sentiment           |