Skip to content

Latest commit

 

History

History
11 lines (7 loc) · 687 Bytes

README.md

File metadata and controls

11 lines (7 loc) · 687 Bytes

sentiment_catalysis

text classification

Using a model trained in Cohere.ai. I trained the model with a dataset from Kaggle.com for detecting emotions like anger, joy, love, sadness, fear and surprise.

In the feedback textarea the text is detected and classify into one of the emotions and then an emoji of the emotion is appearing, except of anger, if so you get a cat to calm down :)

speech recognition and speech to text;

I used JavaScript's "webkitSpeechRecognition();" for speech recognition and then I use a function to transcribe the speech to text in the UI.

The next step is to be able to classify the text from the transcription as I did it for the feedback textarea.