Initial commit with FastAPI + Gradio app

app.py

@@ -29,21 +29,28 @@ def get_similarity(audio1, audio2, sample_rate=16000):
         score, prediction = speaker_verification.verify_batch(signal1, signal2)
         return float(score), "Yes" if prediction else "No"
     except Exception as e:
-        return str(e), None
+        return None, str(e)  # Return error message if any exception
 
 # API function to compare voices
 def compare_voices(file1, file2):
-    # Gradio Audio returns a tuple of (audio, sample_rate)
-    audio1, _ = file1  # Audio1 is a tuple (numpy_array, sample_rate)
-    audio2, _ = file2  # Audio2 is a tuple (numpy_array, sample_rate)
+    try:
+        # Gradio Audio returns a tuple of (audio, sample_rate)
+        audio1, _ = file1  # Audio1 is a tuple (numpy_array, sample_rate)
+        audio2, _ = file2  # Audio2 is a tuple (numpy_array, sample_rate)
+
+        # Get similarity score
+        score, is_same_user = get_similarity(audio1, audio2)
 
-    # Get similarity score
-    score, is_same_user = get_similarity(audio1, audio2)
+        if score is None:
+            # Return the error message if processing fails
+            return {"error": is_same_user}
 
-    if is_same_user is None:
-        return "Error: " + score  # This will return the error message
+        # Return a dictionary with the similarity score and prediction
+        return {"Similarity Score": f"{score:.4f}", "Same User Prediction": is_same_user}
 
-    return {"Similarity Score": f"{score:.4f}", "Same User Prediction": is_same_user}
+    except Exception as e:
+        # Handle unexpected errors
+        return {"error": str(e)}
 
 # FastAPI app
 app = FastAPI()
@@ -53,24 +60,18 @@ async def compare_voices_api(file1: UploadFile = File(...), file2: UploadFile =
     """
     Compare two audio files and return the similarity score and prediction.
     """
-    # Gradio uses numpy arrays directly, so no need to save the files
-    # You'd need to process the audio files here, but in FastAPI you need to convert file to numpy first.
     try:
+        # Process the audio files and return them as numpy arrays
         file1_data = await file1.read()
         file2_data = await file2.read()
 
-        # Convert these file data into numpy arrays (this part is pseudo-code as we need to decode the file data)
-        # Typically, you would use a library like torchaudio or librosa to decode the audio from raw file data.
-        
-        # Assuming audio data is in correct format for the speaker model
-        # Example:
-        # numpy1 = torchaudio.load(io.BytesIO(file1_data))[0].numpy()
-        # numpy2 = torchaudio.load(io.BytesIO(file2_data))[0].numpy()
-
-        # For this example, the audio should be pre-converted to numpy arrays before processing.
+        # You need to process these byte strings into numpy arrays
+        # Assuming the audio is decoded into numpy arrays here (e.g., using torchaudio)
+        # For example:
+        # audio1 = torchaudio.load(io.BytesIO(file1_data))[0].numpy()
+        # audio2 = torchaudio.load(io.BytesIO(file2_data))[0].numpy()
 
-        # Use a conversion library (like torchaudio or librosa) to decode the audio
-        return {"message": "Processing files directly (no save to disk)"}
+        return {"message": "Processing files directly without saving them."}
 
     except Exception as e:
         raise HTTPException(status_code=400, detail=str(e))