Handle 3 types of silences: Indicated by whisper, between tokens, and at the end of the input. Display them in the frontend

whisperlivekit/audio_processor.py

@@ -8,7 +8,7 @@ from datetime import timedelta
 from whisperlivekit.timed_objects import ASRToken
 from whisperlivekit.core import TranscriptionEngine, online_factory
 from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState
-
+from .remove_silences import handle_silences
 # Set up logging once
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
@@ -51,7 +51,6 @@ class AudioProcessor:
         self.tokens = []
         self.buffer_transcription = ""
         self.buffer_diarization = ""
-        self.full_transcription = ""
         self.end_buffer = 0
         self.end_attributed_speaker = 0
         self.lock = asyncio.Lock()
@@ -95,13 +94,12 @@ class AudioProcessor:
         """Convert PCM buffer in s16le format to normalized NumPy array."""
         return np.frombuffer(pcm_buffer, dtype=np.int16).astype(np.float32) / 32768.0
 
-    async def update_transcription(self, new_tokens, buffer, end_buffer, full_transcription, sep):
+    async def update_transcription(self, new_tokens, buffer, end_buffer, sep):
         """Thread-safe update of transcription with new data."""
         async with self.lock:
             self.tokens.extend(new_tokens)
             self.buffer_transcription = buffer
             self.end_buffer = end_buffer
-            self.full_transcription = full_transcription
             self.sep = sep
             
     async def update_diarization(self, end_attributed_speaker, buffer_diarization=""):
@@ -152,7 +150,6 @@ class AudioProcessor:
             self.tokens = []
             self.buffer_transcription = self.buffer_diarization = ""
             self.end_buffer = self.end_attributed_speaker = 0
-            self.full_transcription = self.last_response_content = ""
             self.beg_loop = time()
 
     async def ffmpeg_stdout_reader(self):
@@ -237,7 +234,6 @@ class AudioProcessor:
 
     async def transcription_processor(self):
         """Process audio chunks for transcription."""
-        self.full_transcription = ""
         self.sep = self.online.asr.sep
         cumulative_pcm_duration_stream_time = 0.0
         
@@ -249,7 +245,7 @@ class AudioProcessor:
                     self.transcription_queue.task_done()
                     break
                 
-                if not self.online: # Should not happen if queue is used
+                if not self.online:
                     logger.warning("Transcription processor: self.online not initialized.")
                     self.transcription_queue.task_done()
                     continue
@@ -276,8 +272,6 @@ class AudioProcessor:
 
                 if new_tokens:
                     validated_text = self.sep.join([t.text for t in new_tokens])
-                    self.full_transcription += validated_text
-                    
                     if buffer_text.startswith(validated_text):
                         buffer_text = buffer_text[len(validated_text):].lstrip()
 
@@ -294,7 +288,7 @@ class AudioProcessor:
                 new_end_buffer = max(candidate_end_times)
                 
                 await self.update_transcription(
-                    new_tokens, buffer_text, new_end_buffer, self.full_transcription, self.sep
+                    new_tokens, buffer_text, new_end_buffer, self.sep
                 )
                 self.transcription_queue.task_done()
                 
@@ -382,8 +376,8 @@ class AudioProcessor:
                 lines = []
                 last_end_diarized = 0
                 undiarized_text = []
-                
-                # Process each token
+                current_time = time() - self.beg_loop
+                tokens = handle_silences(tokens, current_time)
                 for token in tokens:
                     speaker = token.speaker
                     

whisperlivekit/remove_silences.py

@@ -0,0 +1,102 @@
+from whisperlivekit.timed_objects import ASRToken
+import re
+
+MIN_SILENCE_DURATION = 4 #in seconds
+
+def blank_to_silence(tokens):
+    full_string = ''.join([t.text for t in tokens])
+    patterns = [re.compile(r'(?:\s*\[BLANK_AUDIO\]\s*)+'), re.compile(r'(?:\s*\[typing\]\s*)+')]             
+    matches = []
+    for pattern in patterns:
+        for m in pattern.finditer(full_string):
+            matches.append({
+                'start': m.start(),
+                'end': m.end()
+            })
+    if matches:
+        # cleaned = pattern.sub(' ', full_string).strip()
+        # print("Cleaned:", cleaned)
+        cumulated_len = 0
+        silence_token = None
+        cleaned_tokens = []
+        for token in tokens:
+            if matches:
+                start = cumulated_len
+                end = cumulated_len + len(token.text)
+                cumulated_len = end
+                if start >= matches[0]['start'] and end <= matches[0]['end']:
+                    if silence_token: #previous token was already silence
+                        silence_token.start = min(silence_token.start, token.start)
+                        silence_token.end = max(silence_token.end, token.end)
+                    else: #new silence
+                        silence_token = ASRToken(
+                            start=token.start,
+                            end=token.end,
+                            speaker=-2,
+                            probability=0.95
+                        )
+                else:
+                    if silence_token: #there was silence but no more
+                        if silence_token.end - silence_token.start >= MIN_SILENCE_DURATION:
+                            cleaned_tokens.append(
+                                silence_token
+                            )
+                        silence_token = None
+                        matches.pop(0)
+                    cleaned_tokens.append(token)
+        # print(cleaned_tokens)    
+        return cleaned_tokens
+    return tokens
+
+def no_token_to_silence(tokens):
+    new_tokens = []
+    silence_token = None
+    for token in tokens:
+        if token.speaker == -2:
+            if new_tokens and new_tokens[-1].speaker == -2: #if token is silence and previous one too
+                new_tokens[-1].end = token.end
+            else:
+                new_tokens.append(token)
+            
+        last_end = new_tokens[-1].end if new_tokens else 0.0
+        if token.start - last_end >= MIN_SILENCE_DURATION: #if token is not silence but important gap
+            if new_tokens and new_tokens[-1].speaker == -2:
+                new_tokens[-1].end = token.start
+            else:
+                silence_token = ASRToken(
+                    start=last_end,
+                    end=token.start,
+                    speaker=-2,
+                    probability=0.95
+                    )
+                new_tokens.append(silence_token)
+        
+        if token.speaker != -2:
+            new_tokens.append(token)
+    return new_tokens
+            
+def ends_with_silence(tokens, current_time):
+    if not tokens:
+        return []
+    last_token = tokens[-1]
+    if tokens and current_time - last_token.end >= MIN_SILENCE_DURATION:
+        if last_token.speaker == -2:
+            last_token.end = current_time
+        else:
+            tokens.append(
+                ASRToken(
+                    start=tokens[-1].end,
+                    end=current_time,
+                    speaker=-2,
+                    probability=0.95
+                )
+            )
+    return tokens
+    
+
+def handle_silences(tokens, current_time):
+    tokens = blank_to_silence(tokens) #useful for simulstreaming backend which tends to generate [BLANK_AUDIO] text
+    tokens = no_token_to_silence(tokens)
+    tokens = ends_with_silence(tokens, current_time)
+    return tokens
+