Update .venv/PythonProjectFile1.py

.venv/PythonProjectFile1.py

@@ -2,19 +2,19 @@ from transformers import pipeline, DistilBertTokenizer, DistilBertForSequenceCla
 import torch
 import gradio as gr
 
-#generator = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english")
+myPipe = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english")
 
-tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
-model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
+#tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
+#model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
 
 def classify_text(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    with torch.no_grad():
-        logits = model(**inputs).logits
-
-    predicted_class_id = logits.argmax().item()
-    return model.config.id2label[predicted_class_id]
+    return myPipe(prompt)[0]
+#    inputs = tokenizer(prompt, return_tensors="pt")
+#    with torch.no_grad():
+#        logits = model(**inputs).logits
+#    predicted_class_id = logits.argmax().item()
+#    return model.config.id2label[predicted_class_id]
 
 # Create a Gradio interface
-iface = gr.Interface(fn=classify_text, inputs="text", outputs="text")
+iface = gr.Interface(fn=classify_text, inputs=gr.Textbox(label="Your Text:"), outputs=gr.Textbox(label="Valence Score:"))
 iface.launch()