raise Exception when language == auto and task == translation

whisperlivekit/audio_processor.py

@@ -120,7 +120,7 @@ class AudioProcessor:
     async def add_dummy_token(self):
         """Placeholder token when no transcription is available."""
         async with self.lock:
-            current_time = time() - self.beg_loop
+            current_time = time() - self.beg_loop if self.beg_loop else 0
             self.tokens.append(ASRToken(
                 start=current_time, end=current_time + 1,
                 text=".", speaker=-1, is_dummy=True
@@ -295,7 +295,7 @@ class AudioProcessor:
                 
                 if type(item) is Silence:
                     cumulative_pcm_duration_stream_time += item.duration
-                    self.online.insert_silence(item.duration, self.tokens[-1].end)
+                    self.online.insert_silence(item.duration, self.tokens[-1].end if self.tokens else 0)
                     continue
                 
                 if isinstance(item, np.ndarray):

whisperlivekit/remove_silences.py

@@ -81,7 +81,7 @@ def ends_with_silence(tokens, buffer_transcription, buffer_diarization, current_
     if not tokens:
         return [], buffer_transcription, buffer_diarization
     last_token = tokens[-1]
-    if tokens and (
+    if tokens and current_time and (
         current_time - last_token.end >= END_SILENCE_DURATION 
         or 
         (current_time - last_token.end >= 3 and vac_detected_silence)

whisperlivekit/simul_whisper/backend.py

@@ -42,6 +42,8 @@ class SimulStreamingOnlineProcessor:
         self.committed: List[ASRToken] = []
         self.last_result_tokens: List[ASRToken] = []
         self.load_new_backend()
+        
+        #can be moved
         if asr.tokenizer:
             self.model.tokenizer = asr.tokenizer
 
@@ -249,11 +251,6 @@ class SimulStreamingASR():
             }
             self.model_path = model_mapping.get(modelsize, f'./{modelsize}.pt')
         
-        # Set up tokenizer for translation if needed
-        if self.task == "translate":
-            self.tokenizer = self.set_translate_task()
-        else:
-            self.tokenizer = None
         self.cfg = AlignAttConfig(
                 model_path=self.model_path,
                 segment_length=self.segment_length,
@@ -271,6 +268,12 @@ class SimulStreamingASR():
                 static_init_prompt=self.static_init_prompt,
         )  
         
+        # Set up tokenizer for translation if needed
+        if self.task == "translate":
+            self.tokenizer = self.set_translate_task()
+        else:
+            self.tokenizer = None
+        
         self.model_name = os.path.basename(self.cfg.model_path).replace(".pt", "")
         self.model_path = os.path.dirname(os.path.abspath(self.cfg.model_path))
         self.models = [self.load_model() for i in range(self.preload_model_count)]
@@ -301,10 +304,12 @@ class SimulStreamingASR():
 
     def set_translate_task(self):
         """Set up translation task."""
+        if self.cfg.language == 'auto':
+            raise Exception('Translation cannot be done with language = auto')
         return tokenizer.get_tokenizer(
             multilingual=True,
-            language=self.model.cfg.language,
-            num_languages=self.model.model.num_languages,
+            language=self.cfg.language,
+            num_languages=99,
             task="translate"
         )