adding latest documentation and changes to the script.

video_transcription/ai_transcriber_v2/main.py

@@ -21,7 +21,7 @@ else:
 from extractor import extract_audio, embed_subtitles
 from transcriber import transcribe_audio, save_as_srt, load_whisper_model
 from translator import translate_with_auto_fallback
-from utils import validate_and_repair_srt, check_srt_duration_match, GracefulKiller, ensure_ollama_running, check_service_availability, check_path_permissions
+from utils import validate_and_repair_srt, check_srt_duration_match, GracefulKiller, ensure_ollama_running, check_service_availability, check_path_permissions, LANGUAGE_MAP
 from diarizer import diarize_audio, merge_diarization_with_transcript
 import tracker
 from tracker import JobStatus
@@ -75,6 +75,7 @@ def process_file(file_path, args, source_lang=None, loaded_model=None, service_s
         transcript_exists = os.path.exists(transcript_file) and not args.force
         
         final_srt_path = transcript_file
+        detected_iso = None
 
         if transcript_exists:
             tracker.logger.info(f"Transcript exists: {transcript_file}. Skipping transcription.")
@@ -84,6 +85,7 @@ def process_file(file_path, args, source_lang=None, loaded_model=None, service_s
             # Use loaded_model if available
             result = transcribe_audio(audio_path, model_size=args.model, language=source_lang, loaded_model=loaded_model)
             segments = result["segments"]
+            detected_iso = result.get("language")
 
             if args.diarize:
                 hf_token = args.hf_token or os.getenv("HF_TOKEN")
@@ -122,8 +124,16 @@ def process_file(file_path, args, source_lang=None, loaded_model=None, service_s
         translation_success = False
         method_used = "None"
 
-        # Check existing
-        if (os.path.exists(base_translated) or os.path.exists(deep_translated) or os.path.exists(local_translated)) and not args.force:
+        # Check if source language matches target language
+        target_iso = LANGUAGE_MAP.get(args.lang)
+        if detected_iso and target_iso and detected_iso == target_iso:
+            tracker.logger.info(f"Source language '{detected_iso}' matches target '{target_iso}'. Skipping translation.")
+            final_srt_path = transcript_file
+            translation_success = True
+            method_used = "Source Match"
+        
+        # Check existing (if not already handled by match)
+        elif (os.path.exists(base_translated) or os.path.exists(deep_translated) or os.path.exists(local_translated)) and not args.force:
              if os.path.exists(local_translated):
                  translated_file = local_translated
                  method_used = "Local LLM (Existing)"