o i@s|dZddlmZmZddlmZddlmZmZddl m Z ddl m Z GdddeZ Gd d d e ZGd d d eZd S)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) MetricsDatac@seZdZdZdZdZdS)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 INCOMPLETErrY/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/audio/turn/base_turn_analyzer.pyr sr c@seZdZdZdS)BaseTurnParamsz(Base class for turn analyzer parameters.N)r r rrrrrrr"src@seZdZdZdddeefddZedefdd Zdefd d Z ee de fd d Z ee de fddZe dede defddZe deeeeffddZdefddZe ddZddZdS)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_ratercCs||_d|_dS)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_rateselfrrrr__init__/s zBaseTurnAnalyzer.__init__returncCs|jS)z|Returns the current sample rate. Returns: int: The effective sample rate for audio processing. )rrrrrr9szBaseTurnAnalyzer.sample_ratecCs|jp||_dS)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. Nrrrrrset_sample_rateBs z BaseTurnAnalyzer.set_sample_ratecCdS)zDetermines if speech has been detected. Returns: bool: True if speech is triggered, otherwise False. Nrrrrrspeech_triggeredMz!BaseTurnAnalyzer.speech_triggeredcCr )zGet the current turn analyzer parameters. Returns: Current turn analyzer configuration parameters. NrrrrrparamsWr"zBaseTurnAnalyzer.paramsbuffer is_speechcCr )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)rr$r%rrr append_audioas zBaseTurnAnalyzer.append_audiocdS)zAnalyzes if an end of turn has occurred based on the audio input. Returns: EndOfTurnState: The result of the end of turn analysis. Nrrrrranalyze_end_of_turnnsz$BaseTurnAnalyzer.analyze_end_of_turnvad_start_secscCr )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)rr)rrrupdate_vad_start_secsws z&BaseTurnAnalyzer.update_vad_start_secscCr )z-Reset the turn analyzer to its initial state.NrrrrrclearszBaseTurnAnalyzer.clearcr')zCleanup the turn analyzer.NrrrrrcleanupszBaseTurnAnalyzer.cleanup)r r rrrintrpropertyrrrboolr!rr#bytesr r&rrr(floatr*r+r,rrrrr(s(     rN)rabcrrenumrtypingrrpydanticrpipecat.metrics.metricsrr rrrrrrs