added

video_transcription/ai_transcriber_v2/translator.py

@@ -22,6 +22,11 @@ def translate_via_ollama(source_srt_content, target_language="English", model="l
         # Using tqdm for progress bar
         for line in tqdm(subs, desc="  Ollama Progress", unit="line"):
             text = line.text.strip()
+            
+            # Skip empty, numeric-only, or extremely short non-word text
+            if not text or text.isdigit() or len(text) < 2:
+                continue
+
             if text:
                 prompt = (
                     f"Translate this subtitle text to {target_language}. Output ONLY the translation.\n"
@@ -54,6 +59,11 @@ def translate_fallback_mymemory(source_srt_content, target_language="en"):
         
         for line in tqdm(subs, desc="  MyMemory Progress", unit="line"):
             text = line.text.strip()
+            
+            # Skip empty, numeric-only, or extremely short non-word text
+            if not text or text.isdigit() or len(text) < 2:
+                continue
+
             if text:
                 if len(text) > 500: # MyMemory has stricter limits often
                      continue
@@ -89,6 +99,11 @@ def translate_fallback_free(source_srt_content, target_language="en"):
         # Simple line-by-line translation
         for line in tqdm(subs, desc="  DeepTranslate Progress", unit="line"):
             text = line.text.strip()
+            
+            # Skip empty, numeric-only, or extremely short non-word text
+            if not text or text.isdigit() or len(text) < 2:
+                continue
+
             if text:
                 # Sanity check: Skip lines that are too long
                 if len(text) > 4000: