Merge branch 'main' of https://huggingface.co/spaces/adannaned/Hate_speech_detection_system

app.py

@@ -1,63 +1,56 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+import torch
+from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
+
+# Load the trained model and tokenizer
+model = DistilBertForSequenceClassification.from_pretrained('best_model')
+tokenizer = DistilBertTokenizer.from_pretrained('best_model')
+
+
+# Define the prediction function
+def predict_hate_speech(text):
+    inputs = tokenizer.encode_plus(
+        text,
+        add_special_tokens=True,
+        max_length=512,
+        padding='max_length',
+        truncation=True,
+        return_tensors='pt'
+    )
+
+    input_ids = inputs['input_ids']
+    attention_mask = inputs['attention_mask']
+
+    with torch.no_grad():
+        outputs = model(input_ids, attention_mask=attention_mask)
+        logits = outputs.logits
+        probabilities = torch.nn.functional.softmax(logits, dim=-1)
+        prediction = torch.argmax(probabilities, dim=1).item()
+
+    labels = {0: 'Neutral', 1: 'Offensive', 2: 'Hateful'}
+    predicted_label = labels[prediction]
+    confidence_scores = {labels[i]: prob for i, prob in enumerate(probabilities[0].tolist())}
+
+    return predicted_label, confidence_scores
+
+# Define the Gradio interface
+interface = gr.Interface(
+    fn=predict_hate_speech,
+    inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs=[
+        gr.Textbox(label="Prediction"),
+        gr.Label(label="Confidence Scores")
     ],
+    title="Hate Speech Detection System using a Deep Active Learning Approach",
+    description="Enter a text to predict whether it is Neutral, Offensive, or Hateful.",
+    examples=[
+        ["I love this product!"],
+        ["You are so stupid!"],
+        ["I hate this!"]
+    ],
+    allow_flagging="manual",
+    flagging_dir="flagged_data"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+interface.launch()

requirements.txt

@@ -1 +1,7 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+torch
+gradio
+transformers
+numpy
+pandas
+scikit-learn