fix Translation imports

whisperlivekit/audio_processor.py

@@ -635,23 +635,23 @@ class AudioProcessor:
             except Exception as e:
                 logger.error(f"Error in watchdog task: {e}", exc_info=True)
         
-async def cleanup(self):
+    async def cleanup(self):
-    """Clean up resources when processing is complete."""
+        """Clean up resources when processing is complete."""
-    logger.info("Starting cleanup of AudioProcessor resources.")
+        logger.info("Starting cleanup of AudioProcessor resources.")
-    self.is_stopping = True
+        self.is_stopping = True
-    for task in self.all_tasks_for_cleanup:
+        for task in self.all_tasks_for_cleanup:
-        if task and not task.done():
+            if task and not task.done():
-            task.cancel()
+                task.cancel()
-        
+            
-        created_tasks = [t for t in self.all_tasks_for_cleanup if t]
+            created_tasks = [t for t in self.all_tasks_for_cleanup if t]
-        if created_tasks:
+            if created_tasks:
-            await asyncio.gather(*created_tasks, return_exceptions=True)
+                await asyncio.gather(*created_tasks, return_exceptions=True)
-        logger.info("All processing tasks cancelled or finished.")
+            logger.info("All processing tasks cancelled or finished.")
-        await self.ffmpeg_manager.stop()
+            await self.ffmpeg_manager.stop()
-        logger.info("FFmpeg manager stopped.")
+            logger.info("FFmpeg manager stopped.")
-        if self.args.diarization and hasattr(self, 'diarization') and hasattr(self.diarization, 'close'):
+            if self.args.diarization and hasattr(self, 'diarization') and hasattr(self.diarization, 'close'):
-            self.diarization.close()
+                self.diarization.close()
-        logger.info("AudioProcessor cleanup complete.")
+            logger.info("AudioProcessor cleanup complete.")
 
 
     async def process_audio(self, message):

whisperlivekit/results_formater.py

@@ -1,7 +1,7 @@
 
 import logging
 from whisperlivekit.remove_silences import handle_silences
-from timed_objects import Line, format_time
+from whisperlivekit.timed_objects import Line, format_time
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)

whisperlivekit/translation/translation.py

@@ -4,7 +4,7 @@ import transformers
 from dataclasses import dataclass
 import huggingface_hub
 from whisperlivekit.translation.mapping_languages import get_nllb_code
-from timed_objects import Translation
+from whisperlivekit.timed_objects import Translation
 
 
 #In diarization case, we may want to translate just one speaker, or at least start the sentences there
@@ -69,7 +69,7 @@ class OnlineTranslation:
         nllb_output_lang = get_nllb_code(output_lang)
             
         source = self.translation_model.tokenizer[input_lang].convert_ids_to_tokens(self.translation_model.tokenizer[input_lang].encode(input))   
-        results = self.translation_model.translator.translate_batch([source], target_prefix=[[nllb_output_lang]])
+        results = self.translation_model.translator.translate_batch([source], target_prefix=[[nllb_output_lang]]) #we can use return_attention=True to try to optimize the stuff.
         target = results[0].hypotheses[0][1:]
         results = self.translation_model.tokenizer[input_lang].decode(self.translation_model.tokenizer[input_lang].convert_tokens_to_ids(target))
         return results
@@ -115,8 +115,23 @@ if __name__ == '__main__':
     output_lang = 'fr'
     input_lang = "en"
     
+    
+    test_string = """
+    Transcription technology has improved so much in the past few years. Have you noticed how accurate real-time speech-to-text is now?
+    """
+    test = test_string.split(' ')
+    step = len(test) // 3
+    
     shared_model = load_model([input_lang])
     online_translation = OnlineTranslation(shared_model, input_languages=[input_lang], output_languages=[output_lang])
+        
+    for id in range(5):
+        val = test[id*step : (id+1)*step]
+        val_str = ' '.join(val)
+        result = online_translation.translate(val_str)
+        print(result)
     
-    result = online_translation.translate('Hello world')
+    
-    print(result)
+    
+    
+    # print(result)