Update app.py

app.py

@@ -21,31 +21,21 @@ LANGUAGE_MAP = {
     "Arabic": "ar"
 }
 
-def analyze_video(video_path, language_display_name, max_speakers, progress=gr.Progress()):
+# app.py
+
+def analyze_video(video_path, max_speakers, progress=gr.Progress()):
     start_time = time.time()
 
     if not video_path:
         return [gr.Markdown("Please upload a video file.")] + [gr.update(visible=False)] * 48 + ["Analysis not started."]
 
-    # Convert the display name to the language code
-    language = LANGUAGE_MAP[language_display_name]
-
     # Start the progress bar
     progress(0, desc="Starting analysis...")
 
-    # Progress for diarization
-    progress(0.2, desc="Starting diarization...")
-    srt_path, diarization_output = process_video(video_path, hf_token, language, max_speakers)
-    progress(0.4, desc="Diarization complete.")
-
-    # Print the diarization results
-    print("Diarization Results:")
-    print(diarization_output)
-
-    # Progress for transcription
-    with open(srt_path, 'r', encoding='utf-8') as file:
-        transcription = file.read()
-    progress(0.6, desc="Transcription complete.")
+    # Progress for transcription and diarization
+    progress(0.2, desc="Starting transcription and diarization...")
+    transcription = diarize_audio(video_path, max_speakers)
+    progress(0.6, desc="Transcription and diarization complete.")
 
     # Progress for processing the transcription
     progress(0.7, desc="Processing transcription...")
@@ -57,9 +47,6 @@ def analyze_video(video_path, language_display_name, max_speakers, progress=gr.P
     charts, explanations = create_charts(results)
     progress(1.0, desc="Charts generation complete.")
 
-    # Clean up the temporary SRT file
-    os.remove(srt_path)
-
     end_time = time.time()
     execution_time = end_time - start_time
 
@@ -104,14 +91,12 @@ def analyze_video(video_path, language_display_name, max_speakers, progress=gr.P
 
     return output_components
 
-
 # Define the Gradio interface
 with gr.Blocks() as iface:
     gr.Markdown("# AI Personality Detection")
     gr.Markdown("Upload a video")
 
     video_input = gr.Video(label="Upload Video")
-    language_input = gr.Dropdown(choices=list(LANGUAGE_MAP.keys()), value="English", label="Select Language")
     max_speakers = gr.Slider(minimum=1, maximum=4, step=1, value=2, label="Maximum Number of Speakers")
 
     analyze_button = gr.Button("Analyze")
@@ -136,7 +121,7 @@ with gr.Blocks() as iface:
 
     analyze_button.click(
         fn=analyze_video,
-        inputs=[video_input, language_input, max_speakers],
+        inputs=[video_input, max_speakers],
         outputs=output_components,
         show_progress=True
     )