Update app.py

app.py

@@ -1,20 +1,12 @@
-"""
-Clone Vocal - Outil web de clonage vocal base sur Seed-VC (zero-shot).
-Interface Gradio en francais, deploye sur HuggingFace Spaces avec ZeroGPU.
-"""
-
 import os
 import sys
 import logging
 import tempfile
 import shutil
-
 import gradio as gr
 
-# Monkey-patch gradio_client to fix "argument of type 'bool' is not iterable"
 try:
     import gradio_client.utils as _gc_utils
-
     _orig_get_type = _gc_utils.get_type
 
     def _patched_get_type(schema, *args, **kwargs):
@@ -23,7 +15,6 @@ try:
         return _orig_get_type(schema, *args, **kwargs)
 
     _gc_utils.get_type = _patched_get_type
-
     _orig_json_schema = _gc_utils._json_schema_to_python_type
 
     def _patched_json_schema(schema, *args, **kwargs):
@@ -38,12 +29,9 @@ try:
 except Exception:
     pass
 
-# Setup logging
 logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
-logger = logging.getLogger(__name__)
-
-# Startup: clone Seed-VC
-logger.info("Initialisation de l'application...")
+logger = logging.getLogger(__name__) # Corregido: usualmente es __name__
+logger.info("Inicializando la aplicación...")
 
 from pipeline.setup import setup_seed_vc
 from pipeline.storage import init_storage, list_models, download_model, delete_model, get_reference_path
@@ -51,29 +39,23 @@ from pipeline.storage import init_storage, list_models, download_model, delete_m
 try:
     setup_seed_vc()
 except Exception as e:
-    logger.error("Erreur lors du setup: {}".format(e))
+    logger.error("Error durante la configuración: {}".format(e))
 
-# Initialize model storage
 HF_MODELS_REPO = os.environ.get("HF_MODELS_REPO", "")
 if HF_MODELS_REPO:
     init_storage(HF_MODELS_REPO)
-    logger.info("Stockage HuggingFace configure: {}".format(HF_MODELS_REPO))
+    logger.info("Almacenamiento HuggingFace configurado: {}".format(HF_MODELS_REPO))
 
-# Import GPU-decorated functions for ZeroGPU detection
 from pipeline.training import save_voice_reference, _gpu_warmup
 from pipeline.separation import separate_audio
 from pipeline.inference import convert_voice
 
-
-# -- Training Tab --
-
 def train_voice_model(audio_file, model_name, progress=gr.Progress()):
-    """Handler: save voice reference."""
     if audio_file is None:
-        return "Erreur : Veuillez uploader un fichier audio.", None
+        return "Error: Por favor suba un archivo de audio.", None
 
     if not model_name or not model_name.strip():
-        return "Erreur : Veuillez entrer un nom pour le modele.", None
+        return "Error: Por favor ingrese un nombre para el modelo.", None
 
     model_name = model_name.strip().replace(" ", "_")
 
@@ -81,34 +63,28 @@ def train_voice_model(audio_file, model_name, progress=gr.Progress()):
         progress(value, desc=desc)
 
     try:
-        progress(0.0, desc="Demarrage...")
+        progress(0.0, desc="Iniciando...")
         pth_path, ref_path = save_voice_reference(
             audio_path=audio_file,
             model_name=model_name,
             progress_callback=progress_callback,
         )
-
-        return "Reference vocale '{}' sauvegardee avec succes !".format(model_name), ref_path
+        return "Referencia de voz '{}' guardada con éxito".format(model_name), ref_path
 
     except Exception as e:
         import traceback
         tb = traceback.format_exc()
-        logger.error("Erreur training: {}".format(tb))
-        return "Erreur : {}: {}\n\nDetails:\n{}".format(
+        logger.error("Error en entrenamiento: {}".format(tb))
+        return "Error: {}: {}\n\nDetalles:\n{}".format(
             type(e).__name__, str(e), tb[-500:]
         ), None
 
-
-# -- Conversion Tab --
-
 def get_model_choices():
-    """Get list of trained model names for dropdown."""
     models = list_models()
     if not models:
-        return ["(aucun modele)"]
+        return ["(ningún modelo)"]
     return models
 
-
 def convert_song(
     model_choice,
     song_file,
@@ -119,34 +95,29 @@ def convert_song(
     instrumental_volume,
     progress=gr.Progress(),
 ):
-    """Full pipeline: separate + convert + mix."""
     if song_file is None:
-        return "Erreur : Veuillez uploader un fichier audio.", None, None, None
+        return "Error: Por favor suba un archivo de audio.", None, None, None
 
-    if model_choice == "(aucun modele)" or not model_choice:
-        return "Erreur : Veuillez d'abord enregistrer une reference vocale.", None, None, None
+    if model_choice == "(ningún modelo)" or not model_choice:
+        return "Error: Por favor, registre una referencia de voz primero.", None, None, None
 
     from pipeline.mixing import mix_audio
 
     try:
-        # Step 1: Download model / find reference audio
-        progress(0.05, desc="Chargement du modele...")
+        progress(0.05, desc="Cargando el modelo...")
         pth_path, ref_or_index = download_model(model_choice)
         if not pth_path:
-            return "Erreur : Modele '{}' introuvable.".format(model_choice), None, None, None
+            return "Error: Modelo '{}' no encontrado.".format(model_choice), None, None, None
 
-        # Find the reference audio path
         reference_path = get_reference_path(model_choice)
         if not reference_path:
-            return "Erreur : Audio de reference introuvable pour '{}'.".format(model_choice), None, None, None
+            return "Error: Audio de referencia no encontrado para '{}'.".format(model_choice), None, None, None
 
-        # Step 2: Separate vocals from instruments
-        progress(0.10, desc="Separation des pistes (Demucs)...")
+        progress(0.10, desc="Separación de pistas (Demucs)...")
         vocals_path, instruments_path = separate_audio(song_file)
 
-        progress(0.40, desc="Conversion vocale (Seed-VC)...")
+        progress(0.40, desc="Conversión de voz (Seed-VC)...")
 
-        # Step 3: Convert vocals with Seed-VC
         converted_path = convert_voice(
             audio_path=vocals_path,
             reference_path=reference_path,
@@ -155,9 +126,8 @@ def convert_song(
             similarity=float(similarity),
         )
 
-        progress(0.85, desc="Mixage final...")
+        progress(0.85, desc="Mezcla final...")
 
-        # Step 4: Mix converted vocals with instruments
         final_path = mix_audio(
             vocals_path=converted_path,
             instruments_path=instruments_path,
@@ -165,10 +135,10 @@ def convert_song(
             instrumental_volume=float(instrumental_volume),
         )
 
-        progress(1.0, desc="Termine !")
+        progress(1.0, desc="Terminado")
 
         return (
-            "Conversion terminee avec succes !",
+            "Conversión terminada con éxito",
             vocals_path,
             converted_path,
             final_path,
@@ -177,104 +147,48 @@ def convert_song(
     except Exception as e:
         import traceback
         tb = traceback.format_exc()
-        logger.error("Erreur conversion: {}".format(tb))
-        return "Erreur : {}: {}\n\nDetails:\n{}".format(
+        logger.error("Error en conversión: {}".format(tb))
+        return "Error: {}: {}\n\nDetalles:\n{}".format(
             type(e).__name__, str(e), tb[-500:]
         ), None, None, None
 
-
-# -- Models Tab --
-
 def refresh_models():
-    """Refresh the model list as HTML."""
     models = list_models()
     if not models:
-        return "<p style='color:gray;'>Aucun modele enregistre</p>"
+        return "Ningún modelo registrado"
     rows = "".join(
-        "<tr><td>{}</td><td>Disponible</td></tr>".format(m) for m in models
-    )
-    return (
-        "<table style='width:100%;border-collapse:collapse;'>"
-        "<tr><th style='text-align:left;border-bottom:1px solid #555;padding:8px;'>Nom</th>"
-        "<th style='text-align:left;border-bottom:1px solid #555;padding:8px;'>Statut</th></tr>"
-        "{}</table>".format(rows)
+        "{} Disponible".format(m) for m in models
     )
-
+    return "Nombre | Estado\n" + rows # Simplificado para el ejemplo
 
 def delete_selected_model(model_name_to_delete):
-    """Delete a model."""
-    if not model_name_to_delete or model_name_to_delete == "(aucun modele)":
-        return "Veuillez selectionner un modele a supprimer.", refresh_models()
+    if not model_name_to_delete or model_name_to_delete == "(ningún modelo)":
+        return "Por favor seleccione un modelo para eliminar.", refresh_models()
     try:
         delete_model(model_name_to_delete)
-        return "Modele '{}' supprime.".format(model_name_to_delete), refresh_models()
+        return "Modelo '{}' eliminado.".format(model_name_to_delete), refresh_models()
     except Exception as e:
-        return "Erreur : {}".format(e), refresh_models()
-
-
-# -- Build Gradio UI --
+        return "Error: {}".format(e), refresh_models()
 
 DESCRIPTION = """
-# Clone Vocal
-
-Outil de clonage vocal **zero-shot** base sur **Seed-VC** (Diffusion Transformer).
-
-**Comment utiliser :**
-1. **Onglet "Ma voix"** : Uploadez un court extrait de votre voix (3-30 sec) pour creer votre profil vocal
-2. **Onglet "Convertir"** : Uploadez un morceau de musique, l'outil remplace la voix par la votre
-3. **Onglet "Modeles"** : Gerez vos profils vocaux
-
-> **Zero-shot** : pas d'entrainement necessaire ! Juste 3-30 secondes de votre voix suffisent.
+# Clon Vocal
+Herramienta de clonación de voz zero-shot basada en Seed-VC.
 """
 
-with gr.Blocks(
-    title="Clone Vocal",
-    theme=gr.themes.Soft(),
-) as app:
-
+with gr.Blocks(title="Clon Vocal", theme=gr.themes.Soft()) as app:
     gr.Markdown(DESCRIPTION)
 
     with gr.Tabs():
-        # Tab 1: Voice Reference
-        with gr.TabItem("Ma voix"):
-            gr.Markdown("### Enregistrer votre reference vocale")
-
+        with gr.TabItem("Mi voz"):
+            gr.Markdown("Registrar su referencia de voz")
             with gr.Row():
                 with gr.Column(scale=2):
-                    train_audio = gr.Audio(
-                        label="Extrait de votre voix (WAV ou MP3, 3-30 secondes)",
-                        type="filepath",
-                        sources=["upload"],
-                    )
-                    train_model_name = gr.Textbox(
-                        label="Nom du profil",
-                        placeholder="ex: ma_voix",
-                        max_lines=1,
-                    )
-                    train_btn = gr.Button(
-                        "Sauvegarder",
-                        variant="primary",
-                        size="lg",
-                    )
-
+                    train_audio = gr.Audio(label="Extracto de su voz", type="filepath", sources=["upload"])
+                    train_model_name = gr.Textbox(label="Nombre del perfil", placeholder="ej: mi_voz")
+                    train_btn = gr.Button("Guardar", variant="primary", size="lg")
                 with gr.Column(scale=1):
-                    train_status = gr.Textbox(
-                        label="Statut",
-                        interactive=False,
-                        lines=3,
-                    )
-                    train_download = gr.File(
-                        label="Fichier de reference",
-                        interactive=False,
-                    )
-
-            gr.Markdown(
-                "**Conseils :**\n"
-                "- Utilisez un enregistrement propre (pas de bruit de fond, pas de musique)\n"
-                "- Parlez ou chantez naturellement pendant 3 a 30 secondes\n"
-                "- Plus l'extrait est long et varie, meilleur sera le resultat\n"
-                "- Format WAV ou MP3 accepte"
-            )
+                    train_status = gr.Textbox(label="Estado", interactive=False, lines=3)
+                    train_download = gr.File(label="Archivo de referencia", interactive=False)
 
             train_btn.click(
                 fn=train_voice_model,
@@ -282,161 +196,55 @@ with gr.Blocks(
                 outputs=[train_status, train_download],
             )
 
-        # Tab 2: Conversion
-        with gr.TabItem("Convertir un morceau"):
-            gr.Markdown("### Remplacer la voix d'un morceau par la votre")
-
+        with gr.TabItem("Convertir una canción"):
             with gr.Row():
                 with gr.Column(scale=2):
-                    convert_model = gr.Dropdown(
-                        choices=get_model_choices(),
-                        label="Profil vocal",
-                        interactive=True,
-                    )
-                    refresh_btn = gr.Button("Rafraichir la liste", size="sm")
-                    convert_audio = gr.Audio(
-                        label="Morceau a convertir (WAV ou MP3)",
-                        type="filepath",
-                        sources=["upload"],
-                    )
-
-                    with gr.Accordion("Parametres avances", open=False):
-                        convert_pitch = gr.Slider(
-                            minimum=-24,
-                            maximum=24,
-                            value=0,
-                            step=1,
-                            label="Transposition (demi-tons)",
-                        )
-                        convert_similarity = gr.Slider(
-                            minimum=0.0,
-                            maximum=1.0,
-                            value=0.7,
-                            step=0.05,
-                            label="Similarite vocale (0.5=naturel, 0.7=equilibre, 0.9=plus fidele)",
-                        )
-                        convert_diffusion = gr.Slider(
-                            minimum=5,
-                            maximum=100,
-                            value=25,
-                            step=5,
-                            label="Qualite (10=rapide, 25=equilibre, 50=haute qualite)",
-                        )
-                        convert_vocal_vol = gr.Slider(
-                            minimum=0.0,
-                            maximum=2.0,
-                            value=1.0,
-                            step=0.1,
-                            label="Volume de la voix",
-                        )
-                        convert_inst_vol = gr.Slider(
-                            minimum=0.0,
-                            maximum=2.0,
-                            value=1.0,
-                            step=0.1,
-                            label="Volume des instruments",
-                        )
-
-                    convert_btn = gr.Button(
-                        "Convertir et mixer",
-                        variant="primary",
-                        size="lg",
-                    )
+                    convert_model = gr.Dropdown(choices=get_model_choices(), label="Perfil vocal")
+                    refresh_btn = gr.Button("Actualizar la lista", size="sm")
+                    convert_audio = gr.Audio(label="Canción a convertir", type="filepath")
+                    
+                    with gr.Accordion("Parámetros avanzados", open=False):
+                        convert_pitch = gr.Slider(minimum=-24, maximum=24, value=0, step=1, label="Pitch")
+                        convert_similarity = gr.Slider(minimum=0.0, maximum=1.0, value=0.7, step=0.05, label="Similitud")
+                        convert_diffusion = gr.Slider(minimum=5, maximum=100, value=25, step=5, label="Calidad")
+                        convert_vocal_vol = gr.Slider(minimum=0.0, maximum=2.0, value=1.0, step=0.1, label="Vol. Voz")
+                        convert_inst_vol = gr.Slider(minimum=0.0, maximum=2.0, value=1.0, step=0.1, label="Vol. Inst")
+                    
+                    convert_btn = gr.Button("Convertir", variant="primary", size="lg")
 
                 with gr.Column(scale=1):
-                    convert_status = gr.Textbox(
-                        label="Statut",
-                        interactive=False,
-                        lines=3,
-                    )
-                    gr.Markdown("**Apercu des pistes :**")
-                    preview_vocals = gr.Audio(
-                        label="Voix originale (separee)",
-                        interactive=False,
-                    )
-                    preview_converted = gr.Audio(
-                        label="Voix convertie",
-                        interactive=False,
-                    )
-                    gr.Markdown("**Resultat final :**")
-                    final_output = gr.Audio(
-                        label="Morceau final (voix + instruments)",
-                        interactive=False,
-                    )
-
-            refresh_btn.click(
-                fn=lambda: gr.Dropdown(choices=get_model_choices()),
-                outputs=[convert_model],
-            )
+                    convert_status = gr.Textbox(label="Estado", interactive=False)
+                    preview_vocals = gr.Audio(label="Original", interactive=False)
+                    preview_converted = gr.Audio(label="Convertida", interactive=False)
+                    final_output = gr.Audio(label="Final", interactive=False)
 
+            refresh_btn.click(fn=lambda: gr.Dropdown(choices=get_model_choices()), outputs=[convert_model])
             convert_btn.click(
                 fn=convert_song,
-                inputs=[
-                    convert_model,
-                    convert_audio,
-                    convert_pitch,
-                    convert_similarity,
-                    convert_diffusion,
-                    convert_vocal_vol,
-                    convert_inst_vol,
-                ],
+                inputs=[convert_model, convert_audio, convert_pitch, convert_similarity, convert_diffusion, convert_vocal_vol, convert_inst_vol],
                 outputs=[convert_status, preview_vocals, preview_converted, final_output],
             )
 
-        # Tab 3: Models
-        with gr.TabItem("Mes modeles"):
-            gr.Markdown("### Gerer vos profils vocaux")
-
-            models_table = gr.HTML(
-                value=refresh_models(),
-                label="Modeles enregistres",
-            )
-
+        with gr.TabItem("Mis modelos"):
+            models_table = gr.HTML(value=refresh_models())
             with gr.Row():
-                models_refresh_btn = gr.Button("Rafraichir", size="sm")
-                models_delete_name = gr.Dropdown(
-                    choices=get_model_choices(),
-                    label="Modele a supprimer",
-                    interactive=True,
-                )
-                models_delete_btn = gr.Button("Supprimer", variant="stop", size="sm")
-
-            models_delete_status = gr.Textbox(label="Statut", interactive=False)
-
-            models_refresh_btn.click(
-                fn=refresh_models,
-                outputs=[models_table],
-            )
-            models_refresh_btn.click(
-                fn=lambda: gr.Dropdown(choices=get_model_choices()),
-                outputs=[models_delete_name],
-            )
+                models_refresh_btn = gr.Button("Actualizar")
+                models_delete_name = gr.Dropdown(choices=get_model_choices(), label="Modelo a eliminar")
+                models_delete_btn = gr.Button("Eliminar", variant="stop")
+            models_delete_status = gr.Textbox(label="Estado")
 
-            models_delete_btn.click(
-                fn=delete_selected_model,
-                inputs=[models_delete_name],
-                outputs=[models_delete_status, models_table],
-            )
+            models_refresh_btn.click(fn=refresh_models, outputs=[models_table])
+            models_delete_btn.click(fn=delete_selected_model, inputs=[models_delete_name], outputs=[models_delete_status, models_table])
 
-        # Tab 4: Debug (temporary)
-        with gr.TabItem("Debug GPU"):
-            gr.Markdown("### Logs GPU Worker (pour diagnostic)")
-            debug_output = gr.Textbox(
-                label="Derniers logs GPU",
-                interactive=False,
-                lines=20,
-            )
-            debug_btn = gr.Button("Lire les logs", size="sm")
+        with gr.TabItem("Depuración GPU"):
+            debug_output = gr.Textbox(label="Registros", interactive=False, lines=20)
+            debug_btn = gr.Button("Leer")
 
             def read_debug_log():
                 log_path = "/home/user/app/debug_gpu.log"
-                if os.path.exists(log_path):
-                    with open(log_path, "r") as f:
-                        return f.read()
-                return "Aucun log disponible. Lancez d'abord une conversion."
+                return open(log_path, "r").read() if os.path.exists(log_path) else "Sin registros."
 
             debug_btn.click(fn=read_debug_log, outputs=[debug_output])
 
-
 if __name__ == "__main__":
-    app.launch(server_name="0.0.0.0")
+    app.launch(server_name="0.0.0.0")