qi(dZddlmZmZddlmZmZddlmZddl m Z ddl m Z ddl mZmZmZddlmZmZmZmZdd lmZdd lmZdd lmZmZdd lmZdd lm Z eGddeZ!dedee"fdZ#GddeZ$y)zBase class for Whisper-based speech-to-text services. This module provides common functionality for services implementing the Whisper API interface, including language mapping, metrics generation, and error handling. ) dataclassfield)AsyncGeneratorOptional)logger AsyncOpenAI) Transcription) ErrorFrameFrameTranscriptionFrame) NOT_GIVEN STTSettings _NotGiven_warn_deprecated_param)WHISPER_TTFS_P99)SegmentedSTTService)Languageresolve_language)time_now_iso8601) traced_sttcfeZdZUdZedZedzezed<edZ e dzezed<y)BaseWhisperSTTSettingszSettings for BaseWhisperSTTService. Parameters: prompt: Optional text to guide the model's style or continue a previous segment. temperature: Sampling temperature between 0 and 1. ctSNrS/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/services/whisper/base_stt.pyzBaseWhisperSTTSettings.'s9r)default_factoryNpromptctSrrrrrr zBaseWhisperSTTSettings.(s)r temperature) __name__ __module__ __qualname____doc__rr"strr__annotations__r$floatrrrrrs;&+;L%MFC$J "M,1BS,TK )Trrlanguagereturnc itjdtjdtjdtjdtj dtj dtjdtjdtjd tjd tjd tjd tjd tjdtjdtj dtj"ditj$dtj&dtj(dtj*dtj,dtj.dtj0dtj2dtj4dtj6dtj8dtj:dtj<dtj>dtj@d tjBd!tjDd"itjFd#tjHd$tjJd%tjLd&tjNd'tjPd(tjRd)tjTd*tjVd+tjXd,tjZd-tj\d.tj^d/tj`d0tjbd1tjdd2tjfd3tjhd4tjjd5tjld6tjnd7tjpd8tjrd9i}tu||d:;S)  T?:@  TA:B  TC:D  TE:F  TG:H  TI:J  TK:L  TM:N  TO:P  TQ:R  TS:T  TU:V  TW:X  TY:Z  T[:\  T]:^  T_:`  Ta:b  Tc:d  Te:f  Tg:h  T T T T T Ts:Lx Hl$ GGrc4eZdZUdZeZeed<ddddddddded dee dee dee d ee d ee d ee d e d e deedee ffdZ dee dee fdZde fdZd e dee fdZe dde de d ee fdZdedeedffdZdedefdZxZS)BaseWhisperSTTServicezBase class for Whisper-based speech-to-text services. Provides common functionality for services implementing the Whisper API interface, including metrics generation and error handling. _settingsNF) modelapi_keybase_urlr,r"r$include_prob_metricspush_empty_transcriptssettingsttfs_p99_latencyrrrr,r"r$rrrrc  tdddd} |tdtd|| _|'tdtd|j|| _|tdtd|| _|tdtd|| _| | j| t |$d| | d| |j|||_ ||_ ||_ y) aInitialize the Whisper STT service. Args: model: Name of the Whisper model to use. .. deprecated:: 0.0.105 Use ``settings=BaseWhisperSTTSettings(model=...)`` instead. api_key: Service API key. Defaults to None. base_url: Service API base URL. Defaults to None. language: Language of the audio input. .. deprecated:: 0.0.105 Use ``settings=BaseWhisperSTTSettings(language=...)`` instead. prompt: Optional text to guide the model's style or continue a previous segment. .. deprecated:: 0.0.105 Use ``settings=BaseWhisperSTTSettings(prompt=...)`` instead. temperature: Sampling temperature between 0 and 1. .. deprecated:: 0.0.105 Use ``settings=BaseWhisperSTTSettings(temperature=...)`` instead. include_prob_metrics: If True, enables probability metrics in API response. Each service implements this differently (see child classes). Defaults to False. push_empty_transcripts: - If true, allow empty `TranscriptionFrame` frames to be pushed downstream instead of discarding them. This is intended for situations where VAD fires even though the user did not speak. In these cases, it is useful to know that nothing was transcribed so that the agent can resume speaking, instead of waiting longer for a transcription. Defaults to False. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark **kwargs: Additional arguments passed to SegmentedSTTService. N)rr,r"r$rr,r"r$)rrr)rrrlanguage_to_service_languager,r"r$ apply_updatesuper__init___create_client_client_include_prob_metrics_push_empty_transcripts)selfrrrr,r"r$rrrrkwargsdefault_settings __class__s rrzBaseWhisperSTTService.__init__sp2     "7,BG L%*  "   ":/Ez R(,(I(I((S  %   "8-CX N&,  #  " "=2H- X+6  (    ) )( 3  -%  **7H= %9"'=$rct||S)N)rrr)rrrs rrz$BaseWhisperSTTService._create_clients7X>>rr-cy)zWhether this service can generate processing metrics. Returns: bool: True, as this service supports metric generation. Tr)rs rcan_generate_metricsz*BaseWhisperSTTService.can_generate_metricss rct|S)zConvert from pipecat Language to service language code. Args: language: The Language enum value to convert. Returns: str or None: The corresponding service language code, or None if not supported. )r)rr,s rrz2BaseWhisperSTTService.language_to_service_languages,H55r transcriptis_finalc Kyw)z+Handle a transcription result with tracing.Nr)rrrr,s r_handle_transcriptionz+BaseWhisperSTTService._handle_transcriptions saudiocXK |jd{|j|d{}|jd{|jj }|st j d|s |jrm|j|d|jjd{t jd|dt||jt|yy7777I#t$r}t!d|Yd}~yd}~wwxYww) aTranscribe audio data to text. Args: audio: Raw audio data to transcribe. Yields: Frame: Either a TranscriptionFrame containing the transcribed text or an ErrorFrame if transcription fails. Nz%Received empty transcription from APITzTranscription: [])resultzUnknown error occurred: )error)start_processing_metrics _transcribestop_processing_metricstextstriprwarningrrrr,debugr _user_idr Exceptionr )rrresponseres rrun_sttzBaseWhisperSTTService.run_stts  C//1 1 1!--e44H..0 0 0==&&(DFGt3300tT^^=T=TUUU /vQ78(MM$&# 4 24 0V C%=aS#AB B B CstD*DC:DC<DC> A-D6D7AD8D*:D<D>DD D' D"D*"D''D*cKtw)aTranscribe audio data to text. Args: audio: Raw audio data in WAV format. Returns: Transcription: Object containing the transcribed text. Raises: NotImplementedError: Must be implemented by subclasses. )NotImplementedError)rrs rrz!BaseWhisperSTTService._transcribes"!s r)r%r&r'r(rSettingsr*rrr)rr+boolrrrrrrbytesrr rr r __classcell__)rs@rrrvsr &H%% $!%"&'+ $'+%*',59,<Z>}Z># Z> 3- Z> 8$ Z> Z>e_Z>#Z>!%Z>12Z>#5/Z>x?hsm?x}?d 6X 6(3- 6NR  )- 9A(9K  !C5!C^E4K-H!CF "u " "rrN)%r( dataclassesrrtypingrrlogururopenair openai.types.audior pipecat.frames.framesr r r pipecat.services.settingsrrrrpipecat.services.stt_latencyrpipecat.services.stt_servicerpipecat.transcriptions.languagerrpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsrrr)rrrrrrs )+,GG__9<F/?  U[ U  UHH8HH HHVr"/r"r