Create app.py

app.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+"""
+Application principale pour Hugging Face Space
+"""
+
+import gradio as gr
+import os
+import tempfile
+from pathlib import Path
+import sys
+
+# Ajouter le dossier courant au path
+sys.path.append(os.path.dirname(__file__))
+
+# Importer les modules nécessaires
+try:
+    from transcribe_audio import transcribe_file, load_whisper_model, get_audio_files
+    from analyze_bob_hf import analyze_files_hf
+    print("✅ Modules importés avec succès")
+except Exception as e:
+    print(f"❌ Erreur d'import: {e}")
+
+def process_audio_file(audio_file):
+    """Traite un fichier audio et retourne les résultats"""
+    try:
+        # Créer des dossiers temporaires
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_path = Path(temp_dir)
+            input_dir = temp_path / "input"
+            output_dir = temp_path / "output"
+            transcriptions_dir = output_dir / "transcriptions"
+            
+            input_dir.mkdir(parents=True, exist_ok=True)
+            output_dir.mkdir(parents=True, exist_ok=True)
+            transcriptions_dir.mkdir(parents=True, exist_ok=True)
+            
+            # Copier le fichier audio
+            audio_path = input_dir / os.path.basename(audio_file)
+            import shutil
+            shutil.copy2(audio_file, audio_path)
+            
+            # Configurer les variables d'environnement
+            os.environ["BOB_INPUT_DIR"] = str(input_dir)
+            os.environ["BOB_TRANSCRIPTIONS_DIR"] = str(transcriptions_dir)
+            os.environ["BOB_OUTPUT_FILE"] = str(output_dir / "resume_bob.txt")
+            os.environ["WHISPER_MODEL"] = "small"  # Modèle léger pour le Space
+            
+            # Transcription
+            print("🔄 Transcription en cours...")
+            model = load_whisper_model("small")
+            success = transcribe_file(model, audio_path, transcriptions_dir)
+            
+            if not success:
+                return "❌ Erreur de transcription", ""
+            
+            # Analyse
+            print("🤖 Analyse en cours...")
+            result = analyze_files_hf(
+                transcriptions_dir=transcriptions_dir,
+                input_dir=input_dir,
+                output_file=output_dir / "resume_bob.txt",
+                log_fn=print
+            )
+            
+            # Lire les résultats
+            resume_path = output_dir / "resume_bob.txt"
+            if resume_path.exists():
+                with open(resume_path, 'r', encoding='utf-8') as f:
+                    resume_content = f.read()
+            else:
+                resume_content = "❌ Fichier de résultat non trouvé"
+            
+            # Lire la transcription
+            transcription_files = list(transcriptions_dir.glob("*.txt"))
+            if transcription_files:
+                with open(transcription_files[0], 'r', encoding='utf-8') as f:
+                    transcription_content = f.read()
+            else:
+                transcription_content = "❌ Transcription non trouvée"
+            
+            return transcription_content, resume_content
+            
+    except Exception as e:
+        return f"❌ Erreur: {str(e)}", f"❌ Erreur: {str(e)}"
+
+# Interface Gradio
+with gr.Blocks(title="BOB Processor") as demo:
+    gr.Markdown("# 🎵 BOB Processor")
+    gr.Markdown("### Transcription et analyse automatique de fichiers audio")
+    
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(
+                label="🎤 Fichier audio à traiter",
+                type="filepath"
+            )
+            process_btn = gr.Button("▶️ Traiter le fichier")
+        
+        with gr.Column():
+            transcription_output = gr.Textbox(
+                label="📝 Transcription",
+                lines=10
+            )
+            resume_output = gr.Textbox(
+                label="📋 Résumé analysé",
+                lines=10
+            )
+    
+    process_btn.click(
+        process_audio_file,
+        inputs=[audio_input],
+        outputs=[transcription_output, resume_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch()