qih.dZddlZddlZddlmZddlmZmZddlZddl m Z ddl m Z ddl mZmZmZddlmZmZdd lmZdd lmZdd lmZmZdd lmZdd lmZdedeefdZ eGddeZ!GddeZ"y)zFal speech-to-text service implementation. This module provides integration with Fal's Wizper API for speech-to-text transcription using segmented audio processing. N) dataclass)AsyncGeneratorOptional)logger) BaseModel) ErrorFrameFrameTranscriptionFrame) STTSettings_warn_deprecated_param) FAL_TTFS_P99)SegmentedSTTService)Languageresolve_language)time_now_iso8601) traced_sttlanguagereturnc 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`d0tjbd1tjdd2tjfd3itjhd4tjjd5tjld6tjnd7tjpd8tjrd9tjtd:tjvd;tjxd<tjzd=tj|d>tj~d?tjd@tjdAtjdBtjdCtjdDitjdEtjdFtjdGtjdHtjdItjdJtjdKtjdLtjdMtjdNtjdOtjdPtjdQtjdRtjdStjdTtjdUtjdVtjdWtjdXtjdYtjdZtjd[tjd\tjd]tjd^tjd_tjd`tjdatjdbi }t||dcdS)ezConvert a Language enum to Fal's Wizper language code. Args: language: The Language enum value to convert. Returns: The corresponding Fal Wizper language code, or None if not supported. afamarasazbabebgbnbobrbscacscydadeeleneseteufafifofrglguhahehihrhthuhyidisitjajwkakkkmknkolalblnloltlvmgmimkmlmnmrmsmtmynenlnnnoocpaplpsptrorusasdsiskslsnsosqsrsusvswtatetgthtktltrttukuruzviyiyozhT) use_base_code)drAFAMARASAZBABEBGBNBOBRBSCACSCYDADEELENESETEUFAFIFOFRGLGUHAHEHIHRHTHUHYIDISITJAJWKAKKKMKNKOLALBLNLOLTLVMGMIMKMLMNMRMSMTMYNENLNNNOOCPAPLPSPTRORUSASDSISKSLSNSOSQSRSUSVSWTATETGTHTKTLTRTTUKURUZVIYIYOZHr)r LANGUAGE_MAPs J/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/services/fal/stt.pylanguage_to_fal_languagersc Tc Tc  Tc  T c  T c  T c  Tc  Tc  Tc  Tc  Tc  Tc  Tc  Tc  Tc  T!c"  T#c$  T%c&  T'c(  T)c*  T+c,  T-c.  T/c0  T1c2  T3c4  T5c6  T7c8  T9c:  T;c<  T=c>  T?c@  TAcB  TCcD  TEcF  TGcH  TIcJ  TKcL  TMcN  TOcP  TQcR  TScT  TUcV  TWcX  TYcZ  T[c\  T]c^  T_c`  Tacb  Tccd  Tecf  Tgch  Ticj  Tkcl  Tmcn  Tocp  Tqcr  Tsct  Tucv  Twcx  Tycz  T{c|  T}c~  Tc@  TAcB  TCcD  TEcF  TGcH  TIcJ  TKcL  TMcN  TOcP  TQcR  TScT  TUcV  TWcX  TYcZ  T[c\  T]c^  T_c`  Tacb  Tccd  Tecf  Tgch  Ticj  Tkcl  T T T T T T T T T T T T TEcLJ Hl$ GGceZdZdZy)FalSTTSettingszSettings for FalSTTService.N)__name__ __module__ __qualname____doc__rrrrs%rrc eZdZUdZeZeed<GddeZdddddddde d d e e d e e jd e d e de de ede ede ede effdZdefdZdede e fdZe dde dede e fdZdedeedffdZxZS) FalSTTServicezSpeech-to-text service using Fal's Wizper API. This service uses Fal's Wizper API to perform speech-to-text transcription on audio segments. It inherits from SegmentedSTTService to handle audio buffering and speech detection. _settingscdeZdZUdZej Zeeed<dZ e ed<dZ e ed<dZ e ed<y ) FalSTTService.InputParamsaConfiguration parameters for Fal's Wizper API. .. deprecated:: 0.0.105 Use ``settings=FalSTTSettings(...)`` instead. Parameters: language: Language of the audio input. Defaults to English. task: Task to perform ('transcribe' or 'translate'). Defaults to 'transcribe'. chunk_level: Level of chunking ('segment'). Defaults to 'segment'. version: Version of Wizper model to use. Defaults to '3'. r transcribetasksegment chunk_level3versionN) rrrrrrrr__annotations__rstrrrrrr InputParamsrs: (0{{(8$2 c $ S$rrNrrr) api_keyaiohttp_sessionrrr sample_rateparamssettingsttfs_p99_latencyrrrrrrrrrc  ftdttj} |t dt|sw|j t|j | _|j dk7r |j }|jdk7r |j}|jdk7r |j}|| j|t |,d || | d| ||_ ||_ ||_|xstj dd |_|j"s t%d ||_|du|_y) ahInitialize the FalSTTService with API key and parameters. Args: api_key: Fal API key. If not provided, will check FAL_KEY environment variable. aiohttp_session: Optional aiohttp ClientSession for HTTP requests. If not provided, a session will be created and managed internally. task: Task to perform (``"transcribe"`` or ``"translate"``). Defaults to ``"transcribe"``. chunk_level: Level of chunking (``"segment"``). Defaults to ``"segment"``. version: Version of Wizper model to use. Defaults to ``"3"``. sample_rate: Audio sample rate in Hz. If not provided, uses the pipeline's rate. params: Configuration parameters for the Wizper API. .. deprecated:: 0.0.105 Use ``settings=FalSTTSettings(...)`` for model/language and direct init parameters for task/chunk_level/version instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark **kwargs: Additional arguments passed to SegmentedSTTService. N)modelrrrrr)rrrFAL_KEYzQFAL_KEY must be provided either through api_key parameter or environment variabler)rrrrr rrrr apply_updatesuper__init___task _chunk_level_versionosgetenv_api_key ValueError_session _owns_session) selfrrrrrrrrrkwargsdefault_settings __class__s rrzFalSTTService.__init__s,L*-hkk:    "8^ <??.0H0Y$-;;,.!;;D%%2"("4"4K>>S($nnG    ) )( 3  #-%    ' ;299Y#; }}c 7F ,4rrcy)zCheck if the service can generate processing metrics. Returns: True, as Fal STT service supports metrics generation. Tr)r s rcan_generate_metricsz"FalSTTService.can_generate_metricss rrct|S)zConvert a Language enum to Fal's service-specific language code. Args: language: The language to convert. Returns: The Fal-specific language code, or None if not supported. )r)r rs rlanguage_to_service_languagez*FalSTTService.language_to_service_language s(11r transcriptis_finalc@K|jd{y7w)z+Handle a transcription result with tracing.N)stop_processing_metrics)r rrrs r_handle_transcriptionz#FalSTTService._handle_transcriptions **,,,s audioc:K |jd{|jstj|_dt j |j }d|i}|jj|jj|d<|j|j|d<|j|j|d<|j|j|d<d|jd d }|jjd || 4d{}|jd k7rI|jd{}t!d|jd| dddd{y|j#d{}dddd{rd|vr|dj%}|r|j'|d|jjd{t)j*d|dt-||j.t1t3|jj|yyyy76717 777#1d{7swYxYw7#t4$r} t!d| Yd} ~ yd} ~ wwxYww)aTranscribes an audio segment using Fal's Wizper API. Args: audio: Raw audio bytes in WAV format (already converted by base class). Yields: Frame: TranscriptionFrame containing the transcribed text, or ErrorFrame on failure. Note: The audio is already in WAV format from the SegmentedSTTService. Only non-empty transcriptions are yielded. Nzdata:audio/x-wav;base64, audio_urlrrrrzKey zapplication/json) Authorizationz Content-Typezhttps://fal.run/fal-ai/wizper)jsonheaderszFal API error (z): )errortextTzTranscription: [])resultzUnknown error occurred: )start_processing_metricsraiohttp ClientSessionbase64 b64encodedecoderrrrrrpoststatusrrrstriprrdebugr _user_idrr Exception) r rdata_uripayloadrresp error_textresponseres rrun_sttzFalSTTService.run_sttsu. C//1 1 1== ' 5 5 7 1&2B2B52I2P2P2R1STH((3G~~&&2&*nn&=&= #zz%"&**  ,)-):): &}}(%)]] "#' !7 2G }}))/* - -;;#%'+yy{!2J$_T[[MZL+YZZ - - -"&, - -Fh.'--/44T4AXAXYYYLL#3D6!;<, (* !8!89' /x? 2( - "3 -- - - - -Z C%=aS#AB B B CsJI3I DI3I I3##II$I+ I36I7I3;J<III I3I A I3)I1*AI3 J I3I3II3II3I."I% #I.*I33 J<JJJJ)N)rrrrrSettingsrrrr rrr#r$intfloatrboolrrrrrbytesrr r4 __classcell__)r s@rrrs> Hi*"&;? $%)(,-1,8P5#P5"'"7"78 P5  P5  P5P5c]P5%P5>*P5#5/P5dd 2X 2(3- 2IM--)--9A#-- ;C5;C^E4K-H;Crr)#rr%r dataclassesrtypingrrr#logururpydanticrpipecat.frames.framesrr r pipecat.services.settingsr r pipecat.services.stt_latencyr pipecat.services.stt_servicerpipecat.transcriptions.languagerrpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsrrrrrrrrrFs  !+GGI5<F/?nHxnHHSMnHb  [   CC'CCr