STT 处理程序在各个会话中保留检测到的语言;只有 Parakeet 会将其重置。

Summary In --language auto, four of the five bundled STT handlers keep self.last_language when a session ends. Pipeline units are reused across clients, so the next client inherits the previous client's detected language. ParakeetTDTSTTHandler — the default backend — already resets it, which is what makes this look like an oversight rather than a policy: # STT/parakeet_tdt_handler.py def on_session_end(self) -> None: super().on_session_end() self.last_language = self.start_language if self.start_language else "en" BaseSTTHandler.on_session_end only clears revision bookkeeping: def on_session_end(self) -> None: if hasattr(self, "_completed_final_revision_keys"): self._completed_final_revision_keys.clear() | handler | resets last_language | --- | --- | parakeet_tdt_handler (default) | yes | whisper_stt_handler | no | mlx_audio_whisper_handler | no | lightning_whisper_mlx_handler | no | qwen3_asr_handler | no on_session_end is the documented place for this — websocket_router._clean_unit describes SESSION_END as "the soft reset signal for stateful handlers", and flushes the queues specifically so work "cannot be picked up by handlers and leak into the next session that claims this unit." ## Impact, per backend I want to be precise rather than overstate this, because it varies: Qwen3-ASR — user-visible. Progressive requests are forced into last_language: # STT/qwen3_asr_handler.py:148 request_language = self.forced_language if request_language is None and progressive: request_language = self.last_language So with --enable_live_transcription, a new client's live partials are transcribed in the previous client's language until their first final turn re-detects. The handler's own docstring says progressive windows reuse "the language of the last final turn" — across a session boundary that's the wrong conversation's last final turn. Whisper family — fallback only. last_language is consulted when detection yields nothing, so the leak surfaces on the new session's first turn only if detection is unavailable or returns an unsupported code. Milder. Note process() copies gen_kwargs (dict(self.gen_kwargs)), so the forced-language kwarg is not mutated at runtime — I checked, and only last_language persists. ## Reproduction No model needed; this is handler state, and it is what SESSION_END is supposed to clear: from speech_to_speech.STT.whisper_stt_handler import WhisperSTTHandler from speech_to_speech.STT.parakeet_tdt_handler import ParakeetTDTSTTHandler w = object.new(WhisperSTTHandler) w.start_language = "auto"; w.last_language = "de"; w.gen_kwargs = {} w.on_session_end() print(w.last_language) # 'de' <- survives into the next session p = object.new(ParakeetTDTSTTHandler) p.start_language = "auto"; p.last_language = "de"; p.enable_live_transcription = False p.on_session_end() …