added more applications

app.py

@@ -6,7 +6,6 @@ from apps.asr import (
 )
 from apps.object_detection import obj_detection_interface
 from apps.image_captioning import img_captioning_interface
-from apps.multimodal_visual_qa import multimodal_visual_qa_interface
 from apps.ner import ner_interface
 
 app = gr.Blocks()
@@ -18,7 +17,6 @@ with app:
             file_transcribe_interface, 
             obj_detection_interface,
             img_captioning_interface,
-            multimodal_visual_qa_interface,
             ner_interface
         ],
         [
@@ -26,7 +24,6 @@ with app:
             "Transcribe from Audio File", 
             "Detect Objects from an Image",
             "Generate a Caption for an Image",
-            "Perform QA on an Image",
             "Named Entity Recogntion"
         ]
     )

apps/multimodal_visual_qa.py

@@ -1,24 +1,24 @@
-import gradio as gr
-from transformers import AutoProcessor
-from transformers import BlipForQuestionAnswering
+# import gradio as gr
+# from transformers import AutoProcessor
+# from transformers import BlipForQuestionAnswering
 
-model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
-processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-base")
+# model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
+# processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-base")
 
-def process_image(image, question: str):
-    inputs = processor(image, question, return_tensors="pt")
-    output = model.generate(**inputs)
-    answer = processor.decode(output[0], skip_special_tokens=True)
+# def process_image(image, question: str):
+#     inputs = processor(image, question, return_tensors="pt")
+#     output = model.generate(**inputs)
+#     answer = processor.decode(output[0], skip_special_tokens=True)
 
-    return answer
+#     return answer
 
-multimodal_visual_qa_interface = gr.Interface(
-    fn=process_image,
-    inputs=[
-        gr.Image(label="Input Image", type="pil"),
-        gr.Textbox(label="Enter question to prompt the image")
-    ],
-    outputs=gr.Textbox(label="Answer"),
-    title="Multimodal Visual QA Application",
-    description="This app can help you ask questions about an image"
-)
+# multimodal_visual_qa_interface = gr.Interface(
+#     fn=process_image,
+#     inputs=[
+#         gr.Image(label="Input Image", type="pil"),
+#         gr.Textbox(label="Enter question to prompt the image")
+#     ],
+#     outputs=gr.Textbox(label="Answer"),
+#     title="Multimodal Visual QA Application",
+#     description="This app can help you ask questions about an image"
+# )

apps/summarizer.py

@@ -0,0 +1,19 @@
+import gradio as gr
+from transformers import pipeline 
+
+summarizer = pipeline("summarization", model="Falconsai/text_summarization")
+
+def summarize(text: str, max_length: int, min_length: int, do_sample: bool=False):
+    result = summarizer(text, max_length, min_length, do_sample)
+    return result["summary_text"]
+
+summarizer_interface = gr.Interface(
+    summarize,
+    inputs=[
+        gr.Textbox(label="Enter the text to be summarized"),
+        gr.Slider(minimum=0, maximum=3000, step=100, label="Max Length", value=1000),
+        gr.Slider(minimum=0, maximum=100, step=10, label="Min Length", value=30),
+        gr.Checkbox(label="Do Sample", value=False)
+    ],
+    outputs=gr.Textbox(label="Summarized Text")
+)