fix webrtc audio problem

nerfreal.py

@@ -167,14 +167,21 @@ class NeRFReal:
                     #print(f'[INFO] get_audio_out shape ',frame.shape)                
                     self.streamer.stream_frame_audio(frame)
             else:
-                frame1 = self.asr.get_audio_out()
+                for _ in range(2):
-                frame2 = self.asr.get_audio_out()
+                    frame = self.asr.get_audio_out()
-                frame = np.concatenate((frame1,frame2))
                     frame = (frame * 32767).astype(np.int16)
                     new_frame = AudioFrame(format='s16', layout='mono', samples=frame.shape[0])
                     new_frame.planes[0].update(frame.tobytes())
                     new_frame.sample_rate=16000
                     asyncio.run_coroutine_threadsafe(audio_track._queue.put(new_frame), loop)
+                # frame1 = self.asr.get_audio_out()
+                # frame2 = self.asr.get_audio_out()
+                # frame = np.concatenate((frame1,frame2))
+                # frame = (frame * 32767).astype(np.int16)
+                # new_frame = AudioFrame(format='s16', layout='mono', samples=frame.shape[0])
+                # new_frame.planes[0].update(frame.tobytes())
+                # new_frame.sample_rate=16000
+                # asyncio.run_coroutine_threadsafe(audio_track._queue.put(new_frame), loop)
             #     frame = (frame * 32767).astype(np.int16).tobytes()
             #     self.fifo_audio.write(frame)           
         else:

webrtc.py

@@ -46,8 +46,8 @@ class PlayerStreamTrack(MediaStreamTrack):
 
         if self.kind == 'video':
             if hasattr(self, "_timestamp"):
-                self._timestamp = (time.time()-self._start) * VIDEO_CLOCK_RATE
+                # self._timestamp = (time.time()-self._start) * VIDEO_CLOCK_RATE
-                # self._timestamp += int(VIDEO_PTIME * VIDEO_CLOCK_RATE)
+                self._timestamp += int(VIDEO_PTIME * VIDEO_CLOCK_RATE)
                 # wait = self._start + (self._timestamp / VIDEO_CLOCK_RATE) - time.time()
                 # if wait>0:
                 #     await asyncio.sleep(wait)
@@ -57,8 +57,8 @@ class PlayerStreamTrack(MediaStreamTrack):
             return self._timestamp, VIDEO_TIME_BASE
         else: #audio
             if hasattr(self, "_timestamp"):
-                self._timestamp = (time.time()-self._start) * SAMPLE_RATE
+                # self._timestamp = (time.time()-self._start) * SAMPLE_RATE
-                # self._timestamp += int(AUDIO_PTIME * SAMPLE_RATE)
+                self._timestamp += int(AUDIO_PTIME * SAMPLE_RATE)
                 # wait = self._start + (self._timestamp / SAMPLE_RATE) - time.time()
                 # if wait>0:
                 #     await asyncio.sleep(wait)