audio_max_len to 30 -> 20, ffmpeg timeout 5 -> 20

whisperlivekit/core.py

@@ -49,7 +49,7 @@ class TranscriptionEngine:
             "frame_threshold": 25,
             "beams": 1,
             "decoder_type": None,
-            "audio_max_len": 30.0,
+            "audio_max_len": 20.0,
             "audio_min_len": 0.0,
             "cif_ckpt_path": None,
             "never_fire": False,
@@ -69,6 +69,8 @@ class TranscriptionEngine:
             config_dict['transcription'] = not kwargs['no_transcription']
         if 'no_vad' in kwargs:
             config_dict['vad'] = not kwargs['no_vad']
+        if 'no_vac' in kwargs:
+            config_dict['vac'] = not kwargs['no_vac']
         
         config_dict.pop('no_transcription', None)
         config_dict.pop('no_vad', None)

whisperlivekit/ffmpeg_manager.py

@@ -143,7 +143,7 @@ class FFmpegManager:
         try:
             data = await asyncio.wait_for(
                 self.process.stdout.read(size),
-                timeout=5.0
+                timeout=20.0
             )
             return data
         except asyncio.TimeoutError:

whisperlivekit/simul_whisper/config.py

@@ -24,6 +24,6 @@ class AlignAttConfig(SimulWhisperConfig):
     segment_length: float = field(default=1.0, metadata = {"help": "in second"})
     frame_threshold: int = 4
     rewind_threshold: int = 200
-    audio_max_len: float = 30.0
+    audio_max_len: float = 20.0
     cif_ckpt_path: str = ""
     never_fire: bool = False