ok

app.py

@@ -9,13 +9,15 @@ from transformers import AutoTokenizer, AutoModelWithLMHead
 model_name="bhadresh-savani/bert-base-go-emotion"
 model = pipeline('text-classification', model_name, truncation=True)
 
+"""
 model_name = "mrm8488/t5-base-finetuned-emotion"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model_t5 = AutoModelWithLMHead.from_pretrained(model_name)
-
+"""
 model_path = "cardiffnlp/twitter-xlm-roberta-base-sentiment"
 sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
 
+"""
 def get_emotion(text):
   input_ids = tokenizer.encode(text + '</s>', return_tensors='pt')
   output = model_t5.generate(input_ids=input_ids, return_dict_in_generate=True, output_scores=True)
@@ -23,7 +25,7 @@ def get_emotion(text):
   dec = [tokenizer.decode(ids) for ids in output.sequences]
   score = transition_scores.min().item()
   return f"{dec[0].replace('<pad>','').replace('</s>','').strip()} [{score}]"
-
+"""
 chat = ChatOpenAI()
 conversation = ConversationChain(llm=chat)  
 #Write a text example of someone angry
@@ -40,12 +42,12 @@ with gr.Blocks() as demo:
         
         l = model(bot_message)[0]
         label_value = f"{l['label']} [{l['score']}]"
-        label_value_t5 = get_emotion(bot_message)
+        #label_value_t5 = get_emotion(bot_message)
         
         s = sentiment_task(bot_message)[0]
         sentiment_value = f"{s['label']} [{s['score']}]"
         
-        return "", chat_history, f"Emotion [1]: {label_value_t5} - Emotion [2]: {label_value} - Sentiment : {sentiment_value}"
+        return "", chat_history, f"Emotion: {label_value} - Sentiment: {sentiment_value}"
 
     msg.submit(respond, [msg, chatbot], [msg, chatbot, label_text])