Upload 4 files

app.py

@@ -0,0 +1,19 @@
+import warnings
+warnings.filterwarnings('ignore')
+import gradio as gr
+
+from ner_utils import ner_with_markdown
+from summerizer_utils import summarizer_with_markdown
+
+
+# Combine both the app
+demo = gr.Blocks()
+with demo:
+    gr.TabbedInterface(
+        [ner_with_markdown, summarizer_with_markdown],
+        ['Named Entity Recognition', 'Text Summarization']
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

ner_utils.py

@@ -0,0 +1,54 @@
+import gradio as gr
+from transformers import pipeline
+
+#Load the NER model
+named_entity_recognizer= pipeline(task = 'ner', model = 'dslim/bert-base-NER')
+# NER helper functions
+def merge_tokens(tokens):
+    merged_tokens = []
+    for token in tokens:
+        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
+            # If current token continues the entity of the last one, merge them
+            last_token = merged_tokens[-1]
+            last_token['word'] += token['word'].replace('##', '')
+            last_token['end'] = token['end']
+            last_token['score'] = (last_token['score'] + token['score']) / 2
+        else:
+            # Otherwise, add the token to the list
+            merged_tokens.append(token)
+
+    return merged_tokens
+def ner(input):
+    output = named_entity_recognizer(input)
+    merged_tokens = merge_tokens(output)
+    return {'text': input, 'entities': merged_tokens}
+
+
+# NER App
+NER = gr.Interface(
+    fn = ner,
+    inputs = [gr.Textbox(label = "Text to find entities", lines = 3)],
+    outputs = [gr.HighlightedText(label = 'Text with entities')],
+    allow_flagging = 'never',
+    examples=[
+        "My name is Nabi, I'm building NER Application",
+    "My name is Emon, I live in Rajshahi and study at RUET"
+    ]
+)
+
+# Add Markdown content
+markdown_content_ner = gr.Markdown(
+    """
+    <div style='text-align: center; font-family: "Times New Roman";'>
+        <h1 style='color: #FF6347;'>Named Entity Recognition APP</h1>
+        <h3 style='color: #4682B4;'>Model: dslim/bert-base-NER</h3>
+        <h3 style='color: #32CD32;'>Made By: Md. Mahmudun Nabi</h3>
+    </div>
+    """
+)
+
+# Combine the Markdown content and the demo interface
+ner_with_markdown = gr.Blocks()
+with ner_with_markdown:
+    markdown_content_ner.render()
+    NER.render()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+transformers

summerizer_utils.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the summarization model
+summarizer = pipeline(task="summarization",
+                      model="sshleifer/distilbart-cnn-12-6")
+
+
+# Function to summarize input text
+def summarize(input,
+              min_length,
+              max_length):
+    output = summarizer(input,
+                        min_length = min_length,
+                        max_length = max_length)
+    return output[0]['summary_text']
+
+# Create the Gradio interface
+SUMMARIZER = gr.Interface(
+    fn=summarize,
+    inputs=[gr.Textbox(label='Text to summarize', lines=6),
+            gr.Slider(label='Min Length', minimum=10, maximum=50, value=10),
+            gr.Slider(label='Max Length', minimum=50, maximum=200, value=100)],
+    outputs=[gr.Textbox(label='Result', lines=3)],
+    allow_flagging='never'
+)
+
+# Add Markdown content
+markdown_content_summarizer = gr.Markdown(
+    """
+    <div style='text-align: center; font-family: "Times New Roman";'>
+        <h1 style='color: #FF6347;'>Text Summarization with DistilBART-CNN</h1>
+        <h3 style='color: #4682B4;'>Model: sshleifer/distilbart-cnn-12-6</h3>
+        <h3 style='color: #32CD32;'>Made By: Md. Mahmudun Nabi</h3>
+    </div>
+    """
+)
+
+# Combine the Markdown content and the demo interface
+summarizer_with_markdown = gr.Blocks()
+with summarizer_with_markdown:
+    markdown_content_summarizer.render()
+    SUMMARIZER.render()