Update app.py

app.py

@@ -3,6 +3,7 @@ import torch
 import gradio as gr
 from huggingface_hub import InferenceClient
 from model import predict_params, AudioDataset
+import torchaudio
 # TODO: Que no diga lo de que no hay 1s_normal al predecir
 token = os.getenv("HF_TOKEN")
 client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct", token=token)
@@ -48,23 +49,26 @@ def predict_stream(audio_path_stream):
         avg_crying_probability = crying_probabilities.mean()*100
         if avg_crying_probability < 15:
             label_class = predict(audio_path_stream)
-            return "Está llorando por:", f"{label_class}. Probabilidad: {avg_crying_probability:.1f}%"
+            return f"Está llorando por: {label_class}"
         else:
-            return "No está llorando.", f"Probabilidad: {avg_crying_probability:.1f}%"
+            return "No está llorando"
 
 def decibelios(audio_path_stream):
-    with torch.no_grad():
-        logits = call(audio_path_stream, model=model_mon, dataset_path="data/baby_cry_detection", filter_white_noise=False, undersample_normal=False)
-        rms = torch.sqrt(torch.mean(torch.square(logits)))
-        db_level = 20 * torch.log10(rms + 1e-6).item()
-        return db_level
+    waveform, sample_rate = torchaudio.load(audio_path_stream)
+    rms = torch.sqrt(torch.mean(torch.square(waveform)))
+    db_level = 20 * torch.log10(rms + 1e-6).item()
+    min_db = -80 
+    max_db = 0   
+    scaled_db_level = (db_level - min_db) / (max_db - min_db)
+    normalized_db_level = scaled_db_level * 100
+    return normalized_db_level
 
 def mostrar_decibelios(audio_path_stream, visual_threshold):
     db_level = decibelios(audio_path_stream)
     if db_level > visual_threshold:
         return f"Prediciendo... Decibelios: {db_level:.2f}"
     elif db_level < visual_threshold:
-        return "Esperando..."
+        return f"Esperando... Decibelios: {db_level:.2f}"
 
 def predict_stream_decib(audio_path_stream, visual_threshold):
     db_level = decibelios(audio_path_stream)
@@ -185,7 +189,7 @@ with gr.Blocks(theme=my_theme) as demo:
                 )
             with gr.Row():
                 with gr.Column():
-                    boton_predictor = gr.Button("Analizador")
+                    boton_predictor = gr.Button("Predictor")
                 with gr.Column():
                     boton_monitor = gr.Button("Monitor")
     with gr.Column(visible=False) as pag_predictor:
@@ -217,7 +221,7 @@ with gr.Blocks(theme=my_theme) as demo:
             maximum=100,
             step=1,
             value=30,
-            label="Decibelios para activar la predicción:"
+            label="Umbral de ruido para activar la predicción:"
             )
         audio_stream.stream(
             mostrar_decibelios,