initial commit

README.md

@@ -1,12 +1,37 @@
 ---
-title: Bangla English Med Bert NER
-emoji: 🚀
-colorFrom: green
-colorTo: blue
+title: Bangla Banglish and English Bio-Medical Entity Recognition
+emoji: 🔍🏷️
+colorFrom: blue
+colorTo: yellow
 sdk: gradio
 sdk_version: 4.41.0
 app_file: app.py
 pinned: false
+license: afl-3.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Named Entity Recognition (NER) App
+
+This application provides a simple interface to perform Named Entity Recognition (NER) on text using a pre-trained model from Hugging Face's Transformers library. The model used under the hood is `dslim/bert-base-NER`, which is designed to identify entities such as names, locations, organizations, and more in a given text.
+
+## Features
+
+- **Named Entity Recognition**: Automatically identify and highlight entities within a given text.
+- **User-Friendly Interface**: Built using Gradio for an easy-to-use web interface.
+
+## Model
+
+- **Model Used**: [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER)
+- **Framework**: Hugging Face Transformers
+
+## Software Packages
+
+- **Gradio**: Used to create the web interface.
+- **Transformers**: Used for model inference.
+- **Spaces**: Utilized for GPU acceleration during model execution.
+
+## How to Use
+
+1. Enter the text you want to analyze in the "Text to find entities" textbox.
+2. Click "Submit" to perform Named Entity Recognition.
+3. The identified entities will be highlighted in the output box.

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+import spaces
+from transformers import pipeline
+from typing import List, Dict, Any
+
+def merge_tokens(tokens: List[Dict[str, any]]) -> List[Dict[str, any]]:
+    """
+    Merges tokens that belong to the same entity into a single token.
+
+    Args:
+        tokens (List[Dict[str, any]]): A list of token dictionaries, each containing information about
+                                       the entity, word, start, end, and score.
+
+    Returns:
+        List[Dict[str, any]]: A list of merged token dictionaries, where tokens that are part of the
+                              same entity are combined into a single token with updated word, end,
+                              and score values.
+    """
+    merged_tokens = []
+    for token in tokens:
+        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
+            # If the 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
+
+# Initialize Model
+get_completion = pipeline("ner", model="kazalbrur/bangla-english-med-bert-ner", device=0)
+
+@spaces.GPU(duration=120)
+def ner(input: str) -> Dict[str, Any]:
+    """
+    Performs Named Entity Recognition (NER) on the given input text and merges tokens that belong
+    to the same entity into a single entity.
+
+    Args:
+        input (str): The input text to analyze for named entities.
+
+    Returns:
+        Dict[str, Any]: A dictionary containing the original text and a list of identified entities
+                        with merged tokens.
+                        - "text": The original input text.
+                        - "entities": A list of dictionaries, where each dictionary contains information
+                          about a recognized entity, including the word, entity type, score, and positions.
+    """
+    output = get_completion(input)
+    merged_tokens = merge_tokens(output)
+    return {"text": input, "entities": merged_tokens}
+
+####### GRADIO APP #######
+title = """<h1 id="title"> Bangla Banglish and English Bio-Medical Entity Recognition </h1>"""
+
+description = """
+- The model used for Recognizing entities [BERT-BASE-NER](https://huggingface.co/kazalbrur/bangla-english-med-bert-ner).
+"""
+
+css = '''
+h1#title {
+  text-align: center;
+}
+'''
+
+theme = gr.themes.Soft()
+demo = gr.Blocks(css=css, theme=theme)
+
+with demo:
+  gr.Markdown(title)
+  gr.Markdown(description)
+  interface = gr.Interface(fn=ner,
+                    inputs=[gr.Textbox(label="Enter Your Text to Find Entities", lines=10)],
+                    outputs=[gr.HighlightedText(label="Text with entities")],
+                    allow_flagging="never",
+)
+
+demo.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch