qidZddlmZmZddlmZddlmZmZddl m Z ddl m Z GddeZ Gd d e ZGd d eZy )zBase turn analyzer for determining end-of-turn in audio conversations. This module provides the abstract base class and enumeration for analyzing when a user has finished speaking in a conversation. )ABCabstractmethod)Enum)OptionalTuple) BaseModel) MetricsDataceZdZdZdZdZy)EndOfTurnStatezState enumeration for end-of-turn analysis results. Parameters: COMPLETE: The user has finished their turn and stopped speaking. INCOMPLETE: The user is still speaking or may continue speaking. N)__name__ __module__ __qualname____doc__COMPLETE INCOMPLETEW/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/audio/turn/base_turn_analyzer.pyr r sHJrr ceZdZdZy)BaseTurnParamsz(Base class for turn analyzer parameters.N)rrrrrrrrr"s2rrceZdZdZdddeefdZedefdZdefdZ ee de fd Z ee de fd Ze d ed e defd Ze deeeeffdZdefdZe dZdZy)BaseTurnAnalyzerzAbstract base class for analyzing user end of turn. This class inherits from BaseObject to leverage its event handling system while still defining an abstract interface through abstract methods. N) sample_raterc ||_d|_y)zInitialize the turn analyzer. Args: sample_rate: Optional initial sample rate for audio processing. If provided, this will be used as the fixed sample rate. rN_init_sample_rate _sample_rateselfrs r__init__zBaseTurnAnalyzer.__init__/s"-rreturnc|jS)z|Returns the current sample rate. Returns: int: The effective sample rate for audio processing. )rr!s rrzBaseTurnAnalyzer.sample_rate9s   rc.|jxs||_y)zSets the sample rate for audio processing. If the initial sample rate was provided, it will use that; otherwise, it sets to the provided sample rate. Args: sample_rate (int): The sample rate to set. Nrr s rset_sample_ratez BaseTurnAnalyzer.set_sample_rateBs!22Akrcy)zDetermines if speech has been detected. Returns: bool: True if speech is triggered, otherwise False. Nrr%s rspeech_triggeredz!BaseTurnAnalyzer.speech_triggeredM rcy)zGet the current turn analyzer parameters. Returns: Current turn analyzer configuration parameters. Nrr%s rparamszBaseTurnAnalyzer.paramsWr*rbuffer is_speechcy)a Appends audio data for analysis. Args: buffer (bytes): The audio data to append. is_speech (bool): Indicates whether the appended audio is speech or not. Returns: EndOfTurnState: The resulting state after appending the audio. Nr)r!r-r.s r append_audiozBaseTurnAnalyzer.append_audioas rc Kyw)zAnalyzes if an end of turn has occurred based on the audio input. Returns: EndOfTurnState: The result of the end of turn analysis. Nrr%s ranalyze_end_of_turnz$BaseTurnAnalyzer.analyze_end_of_turnns  vad_start_secscy)a"Update the VAD start trigger time. The turn analyzer may choose to change its buffer size depending on this value. Args: vad_start_secs (float): The number of seconds of voice activity before triggering the user speaking event. Nr)r!r4s rupdate_vad_start_secsz&BaseTurnAnalyzer.update_vad_start_secsws rcy)z-Reset the turn analyzer to its initial state.Nrr%s rclearzBaseTurnAnalyzer.clears rc Kyw)zCleanup the turn analyzer.Nrr%s rcleanupzBaseTurnAnalyzer.cleanups  r3)rrrrrintr"propertyrr'rboolr)rr,bytesr r0rr r2floatr6r8r:rrrrr(s 8<x}!S!! B3 B $       5  T  n     5+AV1V+W    E     rrN)rabcrrenumrtypingrrpydanticrpipecat.metrics.metricsr r rrrrrrEsA $"/ T  Y b sb r