qidZddlZddlmZmZddlmZddlmZddl m Z ddl m Z ddl mZdd lmZmZd Zd Zd Zd ZGd deZGddeZGddeZy)a$Voice Activity Detection (VAD) analyzer base classes and utilities. This module provides the abstract base class for VAD analyzers and associated data structures for voice activity detection in audio streams. Includes state management, parameter configuration, and audio analysis framework. N)ABCabstractmethod)ThreadPoolExecutor)Enum)Optional)logger) BaseModel)calculate_audio_volume exp_smoothinggffffff?皙?g333333?c eZdZdZdZdZdZdZy)VADStateaVoice Activity Detection states. Parameters: QUIET: No voice activity detected. STARTING: Voice activity beginning, transitioning from quiet. SPEAKING: Active voice detected and confirmed. STOPPING: Voice activity ending, transitioning to quiet. N)__name__ __module__ __qualname____doc__QUIETSTARTINGSPEAKINGSTOPPINGP/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/audio/vad/vad_analyzer.pyrrs EHHHrrcJeZdZUdZeZeed<eZ eed<e Z eed<e Z eed<y) VADParamsa`Configuration parameters for Voice Activity Detection. Parameters: confidence: Minimum confidence threshold for voice detection. start_secs: Duration to wait before confirming voice start. stop_secs: Duration to wait before confirming voice stop. min_volume: Minimum audio volume threshold for voice detection. confidence start_secs stop_secs min_volumeN)rrrrVAD_CONFIDENCEr float__annotations__VAD_START_SECSr! VAD_STOP_SECSr"VAD_MIN_VOLUMEr#rrrrr/s1'J&&J&$Iu$&J&rrceZdZdZddddeedeefdZedefdZ edefd Z edefd Z e defd Z e d edefd ZdefdZdefdZdedefdZd edefdZd edefdZy) VADAnalyzeraAbstract base class for Voice Activity Detection analyzers. Provides the framework for implementing VAD analysis with configurable parameters, state management, and audio processing capabilities. Subclasses must implement the core voice confidence calculation. N) sample_rateparamsr,r-c||_d|_|xs t|_d|_d|_d|_d|_td|_ y)zInitialize the VAD analyzer. Args: sample_rate: Audio sample rate in Hz. If None, will be set later. params: VAD parameters for detection configuration. rrrr ) max_workersN) _init_sample_rate _sample_rater_params _num_channels _vad_buffer_smoothing_factor _prev_volumer _executor)selfr,r-s r__init__zVADAnalyzer.__init__GsR"-, "%,:rreturnc|jS)zdGet the current sample rate. Returns: Current audio sample rate in Hz. )r1r8s rr,zVADAnalyzer.sample_rate]s   rc|jS)zvGet the number of audio channels. Returns: Number of audio channels (always 1 for mono). )r3r<s r num_channelszVADAnalyzer.num_channelsfs!!!rc|jS)zlGet the current VAD parameters. Returns: Current VAD configuration parameters. )r2r<s rr-zVADAnalyzer.paramsos||rcy)zGet the number of audio frames required for analysis. Returns: Number of frames needed for VAD processing. Nrr<s rnum_frames_requiredzVADAnalyzer.num_frames_requiredxs rbuffercy)zCalculate voice activity confidence for the given audio buffer. Args: buffer: Audio buffer to analyze. Returns: Voice confidence score between 0.0 and 1.0. Nr)r8rBs rvoice_confidencezVADAnalyzer.voice_confidences rcd|jxs||_|j|jy)zsSet the sample rate for audio processing. Args: sample_rate: Audio sample rate in Hz. N)r0r1 set_paramsr2)r8r,s rset_sample_ratezVADAnalyzer.set_sample_rates' !22Ak  %rctjd|||_|j|_|j|j zdz|_|j|jz }t|jj|z |_ t|jj|z |_ d|_ d|_tj |_y)zSet VAD parameters and recalculate internal values. Args: params: VAD parameters for detection configuration. zSetting VAD params to: rrN)rdebugr2rA _vad_framesr3_vad_frames_num_bytesr,roundr!_vad_start_framesr"_vad_stop_frames_vad_starting_count_vad_stopping_countrr _vad_state)r8r-vad_frames_per_secs rrFzVADAnalyzer.set_paramss  .vh78 335%)%5%58J8J%JQ%N"!--0@0@@!&t||'>'>AS'S!T %dll&<&>4;M;MvVV Ws?A AA c|xj|z c_|j}t|j|kr |jSt|j|k\r|jd|}|j|d|_|j |}|j |}||_||jjk\xr||jjk\}|r|jxtjk(rtj|_d|_ nxtjk(r|xjdz c_ ntjk(rtj|_d|_n|jxtjk(rtj|_d|_ nXxtjk(rtj|_d|_n'tjk(r|xj dz c_t|j|k\r|jtjk(r5|j|j"k\rtj|_d|_ |jtjk(r5|j |j$k\rtj|_d|_|jS)z2Analyze audio buffer and return current VAD state.Nrr)r4rKlenrQrDrVr6r2r r#rrrrOrrrPrMrN)r8rBnum_required_bytes audio_framesr rUspeakings rr[zVADAnalyzer._run_analyzers& F"!77 t #5 5?? "$""#'99++,?-?@L#//0B0CDD ..|r-rrAbytesr%rDrGrFrVrr^r[rrrr+r+?s 8<[_;x};XiEX;,!S!!"c""  S    u      &3&33&P%PEP %H 6E6h6rr+)rrXabcrrconcurrent.futuresrenumrtypingrlogururpydanticr pipecat.audio.utilsr r r$r'r(r)rrr+rrrrns^#1E  t  ' ' u#ur