first version

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
+
+# Define the model name
+MODEL_NAME = "impresso-project/ner-stacked-bert-multilingual"
+
+# Load the tokenizer and model using the pipeline
+ner_tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+ner_pipeline = pipeline("generic-ner", model=MODEL_NAME, 
+                        tokenizer=ner_tokenizer, 
+                        trust_remote_code=True,
+                        device='cpu')
+
+# Helper function to print entities nicely
+def print_nicely(entities):
+    entity_details = []
+    for entity in entities:
+        entity_info = f"Entity: {entity['entity']} | Confidence: {entity['score']:.2f}% | Text: {entity['word'].strip()} | Start: {entity['start']} | End: {entity['end']}"
+        entity_details.append(entity_info)
+    return "\n".join(entity_details)
+
+# Function to process the sentence and extract entities
+def extract_entities(sentence):
+    results = ner_pipeline(sentence)
+    entity_results = []
+    
+    # Extract and format the entities
+    for key in results.keys():
+        entity_results.append(print_nicely(results[key]))
+    
+    return "\n".join(entity_results)
+
+# Create Gradio interface
+def ner_app_interface():
+    input_sentence = gr.Textbox(lines=5, label="Input Sentence", placeholder="Enter a sentence for NER...")
+    output_entities = gr.Textbox(label="Extracted Entities")
+
+    # Interface definition
+    interface = gr.Interface(
+        fn=extract_entities,
+        inputs=input_sentence,
+        outputs=output_entities,
+        title="Named Entity Recognition",
+        description="Enter a sentence to extract named entities using the NER model from the Impresso project."
+    )
+    
+    interface.launch()
+
+# Run the app
+if __name__ == "__main__":
+    ner_app_interface()
+

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.3.1
+transformers==4.36.0
+sentencepiece