Update app.py

app.py

@@ -1,20 +1,26 @@
 import streamlit as st
 import tensorflow as tf
 
-from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
+from transformers import pipeline
+
+model_ckpt = "Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD"
+
+pipe = pipeline("text clasification", model_ckpt)
+#from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
   
-tokenizer = AutoTokenizer.from_pretrained("Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD")
+#tokenizer = AutoTokenizer.from_pretrained("Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD")
 
-model = TFAutoModelForSequenceClassification.from_pretrained("Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD")
+#model = TFAutoModelForSequenceClassification.from_pretrained("Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD")
 
-labels= model.config.label2id
+#labels= model.config.label2id
 
 text = st.text_area("Enter some text in arabic language!") 
 if text: 
-   out = tf.math.softmax(model(tokenizer(text, padding=True, truncation=True, return_tensors="np")).logits, axis = -1)
-   res = out.numpy()
+   #out = tf.math.softmax(model(tokenizer(text, padding=True, truncation=True, return_tensors="np")).logits, axis = -1)
+  # res = out.numpy()
    
-   labels['NEGATIVE'] = res[0,0]
-   labels['NEUTRAL'] = res[0,1]
-   labels['POSITIVE'] = res[0,2]
-   st.json(labels)
+  # labels['NEGATIVE'] = res[0,0]
+   #labels['NEUTRAL'] = res[0,1]
+   #labels['POSITIVE'] = res[0,2]
+  # st.json(labels)
+  st.json(pipe(text))