save code

core/pipeline.py

@@ -90,12 +90,14 @@ class ChatPipeline:
         for i, seg in enumerate(segments):
             if should_interrupt and should_interrupt():
                 break
-            if on_text_segment is not None:
-                await on_text_segment(seg, i, len(segments))
             seg_audio, seg_sr = await self.tts.synthesize(seg)
+            if should_interrupt and should_interrupt():
+                break
             sr = seg_sr
             if i == 0:
                 first_chunk_ms = int((time.perf_counter() - t0) * 1000)
+            if on_text_segment is not None:
+                await on_text_segment(seg, i, len(segments))
             if on_audio_chunk is not None:
                 await on_audio_chunk(seg_audio, seg_sr, seg, i, len(segments))
             audio_chunks.append(seg_audio)
@@ -122,13 +124,13 @@ class ChatPipeline:
         if on_reply_text is not None:
             await on_reply_text(reply_text)
         llm_latency_ms = int((time.perf_counter() - llm_t0) * 1000)
+        await self.arbitrator.on_avatar_start()
         audio, sr, tts_first_chunk_ms, tts_latency_ms = await self._synthesize_sentence_first(
             reply_text,
             on_audio_chunk=on_audio_chunk,
             on_text_segment=on_reply_segment,
             should_interrupt=lambda: self.arbitrator.cancel_avatar_event.is_set(),
         )
-        await self.arbitrator.on_avatar_start()
         playback_s = max(0.2, min(5.0, float(audio.shape[0]) / float(sr)))
         # Do not block request completion on playback duration.
         asyncio.create_task(self._finish_avatar_after_playback(playback_s))
@@ -157,13 +159,13 @@ class ChatPipeline:
         if on_reply_text is not None:
             await on_reply_text(reply_text)
         llm_latency_ms = int((time.perf_counter() - llm_t0) * 1000)
+        await self.arbitrator.on_avatar_start()
         audio, sr, tts_first_chunk_ms, tts_latency_ms = await self._synthesize_sentence_first(
             reply_text,
             on_audio_chunk=on_audio_chunk,
             on_text_segment=on_reply_segment,
             should_interrupt=lambda: self.arbitrator.cancel_avatar_event.is_set(),
         )
-        await self.arbitrator.on_avatar_start()
         playback_s = max(0.2, min(5.0, float(audio.shape[0]) / float(sr)))
         asyncio.create_task(self._finish_avatar_after_playback(playback_s))
         payload = {

core/state_machine.py

@@ -32,4 +32,5 @@ class Arbitrator:
 
     async def on_avatar_done(self) -> None:
         async with self._lock:
-            self.state = SessionState.IDLE
+            if self.state == SessionState.AVATAR_SPEAKING:
+                self.state = SessionState.IDLE