CLASIFICADOR Y MONITOR FUNCIONANDO A LA VEZ

app.py

@@ -5,15 +5,27 @@ from huggingface_hub import InferenceClient
 from model import model_params, AudioDataset
 
 token = os.getenv("HF_TOKEN")
-# dataset_path = f"data/baby_cry_detection" # PARA MONITOR
-dataset_path = f"data/mixed_data" # PARA CLASIFICADOR
-model, _, _, id2label = model_params(dataset_path)
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")# Usar a GPU o CPU
-model.to(device)# Usar a GPU o CPU
 client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct", token=token)
-# client = InferenceClient("mistralai/Mistral-Nemo-Instruct-2407", token=token)
 
-def predict(audio_path):
+def predict_class(audio_path):
+    dataset_path = f"data/mixed_data" # PARA CLASIFICADOR
+    model, _, _, id2label = model_params(dataset_path)
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")# Usar a GPU o CPU
+    model.to(device)# Usar a GPU o CPU
+    audio_dataset = AudioDataset(dataset_path, {})
+    inputs = audio_dataset.preprocess_audio(audio_path)
+    inputs = {"input_values": inputs.to(device).unsqueeze(0)}
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predicted_class_ids = outputs.logits.argmax(-1)
+        label = id2label[predicted_class_ids.item()]
+    return label
+
+def predict_mon(audio_path):
+    dataset_path = f"data/baby_cry_detection" # PARA CLASIFICADOR
+    model, _, _, id2label = model_params(dataset_path)
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")# Usar a GPU o CPU
+    model.to(device)# Usar a GPU o CPU
     audio_dataset = AudioDataset(dataset_path, {})
     inputs = audio_dataset.preprocess_audio(audio_path)
     inputs = {"input_values": inputs.to(device).unsqueeze(0)}
@@ -149,7 +161,7 @@ with gr.Blocks(theme=my_theme) as demo:
                     )
                 classify_btn = gr.Button("¿Por qué llora?")
                 classification_output = gr.Textbox(label="Tu bebé llora por:")
-                classify_btn.click(predict, inputs=audio_input, outputs=classification_output)
+                classify_btn.click(predict_class, inputs=audio_input, outputs=classification_output)
             with gr.Column():
                 gr.Markdown("<h2>Assistant</h2>")
                 system_message = "You are a Chatbot specialized in baby health and care."
@@ -168,7 +180,34 @@ with gr.Blocks(theme=my_theme) as demo:
                 gr.Markdown("Este chatbot no sustituye a un profesional de la salud. Ante cualquier preocupación o duda, consulta con tu pediatra.")
                 boton_volver_inicio_1 = gr.Button("Volver a la pantalla inicial").click(cambiar_pestaña, outputs=[pagina_1, pantalla_inicial])
     with gr.Column(visible=False) as pagina_2:
-        gr.Markdown("<h2>Monitor</h2>")
+        with gr.Row():
+            with gr.Column():
+                gr.Markdown("<h2>Monitor</h2>")
+                audio_input = gr.Audio(
+                    min_length=1.0,
+                    format="wav",
+                    label="Baby recorder",
+                    type="filepath", # Para no usar numpy y preprocesar siempre igual
+                    )
+                classify_btn = gr.Button("¿Por qué llora?")
+                classification_output = gr.Textbox(label="Tu bebé llora por:")
+                classify_btn.click(predict_mon, inputs=audio_input, outputs=classification_output)
+            with gr.Column():
+                gr.Markdown("<h2>Assistant</h2>")
+                system_message = "You are a Chatbot specialized in baby health and care."
+                max_tokens = 512
+                temperature = 0.7
+                top_p = 0.95
+                chatbot = gr.ChatInterface(
+                    respond, # TODO: Cambiar para que argumentos estén aquí metidos
+                    additional_inputs=[
+                        gr.State(value=system_message),
+                        gr.State(value=max_tokens),
+                        gr.State(value=temperature),
+                        gr.State(value=top_p)
+                    ],
+                )
+                gr.Markdown("Este chatbot no sustituye a un profesional de la salud. Ante cualquier preocupación o duda, consulta con tu pediatra.")
         gr.Markdown("Contenido de la Página 2")
         boton_volver_inicio_2 = gr.Button("Volver a la pantalla inicial").click(cambiar_pestaña, outputs=[pagina_2, pantalla_inicial])
     boton_pagina_1.click(cambiar_pestaña, outputs=[pantalla_inicial, pagina_1])