Update main.py

main.py

@@ -5,38 +5,24 @@ import librosa
 from fastapi import FastAPI, Header, HTTPException, Depends
 from pydantic import BaseModel
 from transformers import pipeline
-
-# =========================
-# CONFIG
-# =========================
 API_KEY = "SynxsOG"
 SUPPORTED_LANGUAGES = {"Tamil", "English", "Hindi", "Malayalam", "Telugu"}
 MODEL_NAME = "MelodyMachine/Deepfake-audio-detection-V2"
-
-# Load the model - This model uses LABEL_0 for Human and LABEL_1 for AI
 detector = pipeline("audio-classification", model=MODEL_NAME)
-
 app = FastAPI(title="AI Generated Voice Detection API")
-
 class VoiceRequest(BaseModel):
     language: str
     audioFormat: str
     audioBase64: str
-
 def verify_api_key(x_api_key: str = Header(None)):
     if x_api_key != API_KEY:
         raise HTTPException(status_code=401, detail="Invalid API key")
     return x_api_key
-
-# =========================
-# AUDIO & FORENSIC UTILS
-# =========================
 def load_audio(base64_audio: str):
     clean_base64 = base64_audio.split(",")[-1]
     audio_bytes = base64.b64decode(clean_base64)
     y, sr = librosa.load(io.BytesIO(audio_bytes), sr=16000)
     return y, sr
-
 def get_forensics(y, sr):
     # Forensic analysis to check for natural variation
     pitch = librosa.yin(y, fmin=50, fmax=300)
@@ -44,55 +30,31 @@ def get_forensics(y, sr):
     rms = librosa.feature.rms(y=y)[0]
     rms_std = np.std(rms)
     return {"pitch_std": pitch_std, "rms_std": rms_std}
-
-# =========================
-# FIXED HYBRID LOGIC
-# =========================
 def hybrid_decision(model_label, model_score, forensic_data):
-    # CRITICAL FIX 1: Correct Label Mapping
-    # LABEL_1 is AI/Fake, LABEL_0 is Human/Real
     if model_label == "LABEL_1":
         is_ai = True
         base_prob = model_score
     else:
         is_ai = False
-        base_prob = 1 - model_score # Convert human score to AI probability
-
-    # CRITICAL FIX 2: Realistic Forensic Penalties
-    # If it looks like a human (high variation), reduce AI probability
+        base_prob = 1 - model_score 
     adjustment = 0
     if forensic_data["pitch_std"] > 15:
         adjustment -= 0.10
     if forensic_data["rms_std"] > 0.01:
         adjustment -= 0.05
-
     final_ai_prob = max(0.01, min(base_prob + adjustment, 0.99))
-
-    # CRITICAL FIX 3: Result Logic
-    if final_ai_prob > 0.5:
+    if final_ai_prob <0.5:
         return "AI_GENERATED", round(final_ai_prob, 4)
     else:
-        # Confidence in it being human is 1 - AI probability
         return "HUMAN", round(1 - final_ai_prob, 4)
-
-# =========================
-# API ENDPOINT
-# =========================
 @app.post("/api/voice-detection")
 async def detect_voice(data: VoiceRequest, api_key: str = Depends(verify_api_key)):
     try:
         y, sr = load_audio(data.audioBase64)
-        
-        # 1. Get Model Prediction
         preds = detector(y)
         top = preds[0]
-        
-        # 2. Get Forensic Data
         f_data = get_forensics(y, sr)
-        
-        # 3. Get Hybrid Result
         classification, confidence = hybrid_decision(top["label"], top["score"], f_data)
-        
         return {
             "status": "success",
             "classification": classification,