Update app.py

app.py

@@ -9,7 +9,7 @@ from llm import query_llm, extract_structured_data
 from reporting import generate_enhanced_csv, generate_enhanced_pdf
 from dashboard import generate_comprehensive_dashboard
 from validation import validate_transcript_quality, check_data_completeness
-from audio_transcriber import transcribe_with_diarization_streaming
+
 
 # HuggingFace Spaces Configuration
 import os
@@ -18,27 +18,7 @@ os.environ["LLM_TIMEOUT"] = "25"
 os.environ["MAX_TOKENS_PER_REQUEST"] = "100"
 print("🚀 Running on HuggingFace Spaces - Optimized Configuration Loaded")
 
-def preprocess_audio(audio_files, num_speakers):
-    """Convert audio to transcripts"""
-    if not audio_files:
-        return None, "No audio files provided"
-    
-    transcript_paths = []
-    status = ""
-    
-    for audio in audio_files:
-        try:
-            # Get the actual file path
-            audio_path = audio.name if hasattr(audio, 'name') else str(audio)
-            
-            transcript_path = transcribe_with_diarization(audio_path, num_speakers)
-            transcript_paths.append(transcript_path)
-            status += f"✓ {os.path.basename(audio_path)} → {transcript_path}\n"
-        except Exception as e:
-            status += f"✗ {os.path.basename(audio_path)}: {str(e)}\n"
-    
-    # Return list of paths for file component
-    return transcript_paths if transcript_paths else None, status
+
 
 
 def analyze(files, file_type, user_comments, role_hint, debug_mode, interviewee_type, progress=gr.Progress()):
@@ -510,40 +490,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     
     with gr.Tabs():
      
-        with gr.TabItem("🎤 Audio Preprocessing"):
-            gr.Markdown("""
-            Upload audio interviews to auto-transcribe with speaker identification.
-            Outputs DOCX files ready for analysis.
-            """)
-            
-            with gr.Row():
-                audio_input = gr.File(
-                    label="Upload Audio Files",
-                    file_types=[".mp3", ".wav", ".m4a", ".flac"],
-                    file_count="multiple"
-                )
-                num_speakers_input = gr.Slider(
-                    minimum=1,
-                    maximum=5,
-                    value=2,
-                    step=1,
-                    label="Number of Speakers"
-                )
-            
-            transcribe_btn = gr.Button("🎙️ Transcribe Audio", variant="primary")
-            transcribe_status = gr.Textbox(label="Status", lines=10)
-            transcript_files = gr.File(label="Download Transcripts", file_count="multiple")
-            
-            transcribe_btn.click(
-                fn=preprocess_audio,
-                inputs=[audio_input, num_speakers_input],
-                outputs=[transcript_files, transcribe_status]
-            )
-            
-            gr.Markdown("""
-            **Next:** Download transcripts, then go to "Transcript Analysis" tab to analyze them.
-            """)
-        
         
               
         with gr.TabItem("📊 Transcript Analysis"):