asr_timestamp_transcription+diarization

app.py

@@ -1,17 +1,17 @@
 import gradio as gr
 from audio_processing import process_audio, print_results
 def transcribe_audio(audio_file):
-    language_segments, text_segments = process_audio(audio_file)
+    language_segments, final_segments = process_audio(audio_file)
     
     output = "Detected language changes:\n\n"
-    for lang_segment in language_segments:
-        output += f"Language: {lang_segment['language']}\n"
-        output += f"Time: {lang_segment['start']:.2f}s - {lang_segment['end']:.2f}s\n\n"
-
-    output += "Transcription:\n\n"
-    for segment in text_segments:
-        output += f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}\n"
+    for segment in language_segments:
+        output += f"Language: {segment['language']}\n"
+        output += f"Time: {segment['start']:.2f}s - {segment['end']:.2f}s\n\n"
 
+    output += "Transcription with language detection and speaker diarization:\n\n"
+    for segment in final_segments:
+        output += f"[{segment['start']:.2f}s - {segment['end']:.2f}s] ({segment['language']}) Speaker {segment['speaker']}: {segment['text']}\n"
+        # output += f"[{segment['start']:.2f}s - {segment['end']:.2f}s] ({segment['language']}): {segment['text']}\n"
     return output
 
 iface = gr.Interface(