Added audio task

tasks/audio.py

@@ -1,32 +1,92 @@
 from fastapi import APIRouter
+from datetime import datetime
+from datasets import load_dataset
+from sklearn.metrics import accuracy_score
+import random
+
 from .utils.evaluation import AudioEvaluationRequest
-from .utils.emissions import get_space_info
+from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
 router = APIRouter()
 
 DESCRIPTION = "Random Baseline"
 ROUTE = "/audio"
 
+
 @router.post(ROUTE, tags=["Audio Task"],
              description=DESCRIPTION)
 async def evaluate_audio(request: AudioEvaluationRequest):
     """
-    Evaluate audio classification.
+    Evaluate audio classification for rainforest sound detection.
     
     Current Model: Random Baseline
-    - Makes random predictions
+    - Makes random predictions from the label space (0-1)
     - Used as a baseline for comparison
     """
+    # Get space info
     username, space_url = get_space_info()
-    return {
-        "message": "Audio evaluation endpoint not yet implemented",
+
+    # Define the label mapping
+    LABEL_MAPPING = {
+        "chainsaw": 0,
+        "environment": 1
+    }
+
+    try:
+        from huggingface_hub import login
+        login()
+    except:
+        pass
+
+    # Load and prepare the dataset
+    dataset = load_dataset(request.dataset_name)
+
+    # Convert string labels to integers
+    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
+
+    # Split dataset
+    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
+    test_dataset = train_test["test"]
+    
+    # Start tracking emissions
+    tracker.start()
+    tracker.start_task("inference")
+    
+    #--------------------------------------------------------------------------------------------
+    # YOUR MODEL INFERENCE CODE HERE
+    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
+    #--------------------------------------------------------------------------------------------   
+    
+    # Make random predictions (placeholder for actual model inference)
+    true_labels = test_dataset["label"]
+    predictions = [random.randint(0, 1) for _ in range(len(true_labels))]
+    
+    #--------------------------------------------------------------------------------------------
+    # YOUR MODEL INFERENCE STOPS HERE
+    #--------------------------------------------------------------------------------------------   
+    
+    # Stop tracking emissions
+    emissions_data = tracker.stop_task()
+    
+    # Calculate accuracy
+    accuracy = accuracy_score(true_labels, predictions)
+    
+    # Prepare results dictionary
+    results = {
         "username": username,
         "space_url": space_url,
+        "submission_timestamp": datetime.now().isoformat(),
         "model_description": DESCRIPTION,
-        "route": ROUTE,
-        "received_config": {
+        "accuracy": float(accuracy),
+        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
+        "emissions_gco2eq": emissions_data.emissions * 1000,
+        "emissions_data": clean_emissions_data(emissions_data),
+        "api_route": ROUTE,
+        "dataset_config": {
             "dataset_name": request.dataset_name,
             "test_size": request.test_size,
             "test_seed": request.test_seed
         }
-    } 
+    }
+    
+    return results 

tasks/utils/evaluation.py

@@ -10,9 +10,9 @@ class TextEvaluationRequest(BaseEvaluationRequest):
                             description="The name of the dataset on HuggingFace Hub")
 
 class ImageEvaluationRequest(BaseEvaluationRequest):
-    dataset_name: str = Field("placeholder/frugalaichallenge-image-train", 
+    dataset_name: str = Field("pyronear/pyro-sdis", 
                             description="The name of the dataset on HuggingFace Hub")
 
 class AudioEvaluationRequest(BaseEvaluationRequest):
-    dataset_name: str = Field("placeholder/frugalaichallenge-audio-train", 
+    dataset_name: str = Field("rfcx/frugalai", 
                             description="The name of the dataset on HuggingFace Hub")