feat:add logs

tasks/audio.py

@@ -42,10 +42,12 @@ async def evaluate_audio(request: AudioEvaluationRequest):
     # Load and prepare the dataset
     # Because the dataset is gated, we need to use the HF_TOKEN environment variable to authenticate
     dataset = load_dataset(request.dataset_name,token=os.getenv("HF_TOKEN"))
+    print('dataset loaded')
     
     # Split dataset
     train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
     test_dataset = train_test["test"]
+    print('train/test splitted')
     
     # Start tracking emissions
     tracker.start()
@@ -63,6 +65,7 @@ async def evaluate_audio(request: AudioEvaluationRequest):
 
     def predict_new_audio(model, dataset, sr):
         list_mfcc = [compute_mfcc(row, sr) for row in dataset]
+        print('mfcc computed')
         array_mfcc = np.vstack(list_mfcc)
         predictions = model.predict(array_mfcc)
         return predictions
@@ -70,7 +73,11 @@ async def evaluate_audio(request: AudioEvaluationRequest):
     model_filename = "lightgbm_baseline_87_acc.pkl"
     clf = joblib.load(model_filename)
 
+    print('model loaded')
+
     predictions = predict_new_audio(clf, test_dataset, 12000)
+
+    print('predictions done')
     
     #--------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE