Update app.py

app.py

@@ -1,63 +1,101 @@
 import streamlit as st
 from transformers import pipeline
+from transformers import AutoModelForSequenceClassification
+from transformers import AutoTokenizer
+import torch
+import numpy as np
 
-# img2text
-def img2text(url):
-    image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
-    text = image_to_text_model(url)[0]["generated_text"]
+def main():
 
-    print(text)
-    return text
 
-# txt2Story
-def txt2story(text):
-    pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
-    story_txt = pipe(text)[0]['generated_text']
+    st.title("yelp2024fall Test")
+    st.write("Enter a sentence for analysis:")
 
-    print(story_txt)
-    return story_txt
+    user_input = st.text_input("")
+    if user_input:
+        # Approach: AutoModel
+        model2 = AutoModelForSequenceClassification.from_pretrained("isom5240/CustomModel_yelp2024fall",
+                                                                    num_labels=5)
+        tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
 
-# Story2Audio
-def text2audio(story_text):
-    pipe = pipeline("text-to-audio", model="Matthijs/mms-tts-eng")
-    audio_data = pipe(story_text)
-    return audio_data
+        inputs = tokenizer(user_input,
+                        padding=True,
+                        truncation=True,
+                        return_tensors='pt')
 
+        outputs = model2(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        predictions = predictions.cpu().detach().numpy()
+        # Get the index of the largest output value
+        max_index = np.argmax(predictions)
+        st.write(f"result (AutoModel) - Label: {max_index}")
 
-def main():
-    st.set_page_config(page_title="Your Image to Audio Story", page_icon="🦜")
-    st.header("Turn Your Image to Audio Story")
-    uploaded_file = st.file_uploader("Select an Image...")
 
-    if uploaded_file is not None:
-        print(uploaded_file)
-        bytes_data = uploaded_file.getvalue()
-        with open(uploaded_file.name, "wb") as file:
-            file.write(bytes_data)
-        st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
+if __name__ == "__main__":
+    main()
 
 
-        #Stage 1: Image to Text
-        st.text('Processing img2text...')
-        scenario = img2text(uploaded_file.name)
-        st.write(scenario)
 
-        #Stage 2: Text to Story
-        st.text('Generating a story...')
-        story = txt2story(scenario)
-        st.write(story)
+# import streamlit as st
+# from transformers import pipeline
 
-        #Stage 3: Story to Audio data
-        st.text('Generating audio data...')
-        audio_data =text2audio(story)
+# # img2text
+# def img2text(url):
+#     image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
+#     text = image_to_text_model(url)[0]["generated_text"]
 
-        # Play button
-        if st.button("Play Audio"):
-            st.audio(audio_data['audio'],
-                     format="audio/wav",
-                     start_time=0,
-                     sample_rate = audio_data['sampling_rate'])
+#     print(text)
+#     return text
 
+# # txt2Story
+# def txt2story(text):
+#     pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+#     story_txt = pipe(text)[0]['generated_text']
 
-if __name__ == "__main__":
-    main()
+#     print(story_txt)
+#     return story_txt
+
+# # Story2Audio
+# def text2audio(story_text):
+#     pipe = pipeline("text-to-audio", model="Matthijs/mms-tts-eng")
+#     audio_data = pipe(story_text)
+#     return audio_data
+
+
+# def main():
+#     st.set_page_config(page_title="Your Image to Audio Story", page_icon="🦜")
+#     st.header("Turn Your Image to Audio Story")
+#     uploaded_file = st.file_uploader("Select an Image...")
+
+#     if uploaded_file is not None:
+#         print(uploaded_file)
+#         bytes_data = uploaded_file.getvalue()
+#         with open(uploaded_file.name, "wb") as file:
+#             file.write(bytes_data)
+#         st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
+
+
+#         #Stage 1: Image to Text
+#         st.text('Processing img2text...')
+#         scenario = img2text(uploaded_file.name)
+#         st.write(scenario)
+
+#         #Stage 2: Text to Story
+#         st.text('Generating a story...')
+#         story = txt2story(scenario)
+#         st.write(story)
+
+#         #Stage 3: Story to Audio data
+#         st.text('Generating audio data...')
+#         audio_data =text2audio(story)
+
+#         # Play button
+#         if st.button("Play Audio"):
+#             st.audio(audio_data['audio'],
+#                      format="audio/wav",
+#                      start_time=0,
+#                      sample_rate = audio_data['sampling_rate'])
+
+
+# if __name__ == "__main__":
+#     main()