o i .@sdZddlZddlZddlmZddlmZmZddlZddl m Z ddl m Z ddl mZmZmZddlmZdd lmZdd lmZdd lmZmZdd lmZdd lmZdedeefddZeGdddeZ GdddeZ!dS)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) FAL_TTFS_P99)SegmentedSTTService)Languageresolve_language)time_now_iso8601) traced_sttlanguagereturncCsitjdtjdtjdtjdtjdtjdtjdtjdtj d tj d tj d tj d tj d tjdtjdtjdtjditjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtj d tj!d!tj"d"itj#d#tj$d$tj%d%tj&d&tj'd'tj(d(tj)d)tj*d*tj+d+tj,d,tj-d-tj.d.tj/d/tj0d0tj1d1tj2d2tj3d3itj4d4tj5d5tj6d6tj7d7tj8d8tj9d9tj:d:tj;d;tjd>tj?d?tj@d@tjAdAtjBdBtjCdCtjDdDitjEdEtjFdFtjGdGtjHdHtjIdItjJdJtjKdKtjLdLtjMdMtjNdNtjOdOtjPdPtjQdQtjRdRtjSdStjTdTtjUdUtjVdVtjWdWtjXdXtjYdYtjZdZtj[d[tj\d\tj]d]tj^d^tj_d_tj`d`tjadatjbdbi }tc||dcddS)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)dr AFAMARASAZBABEBGBNBOBRBSCACSCYDADEELENESETEUFAFIFOFRGLGUHAHEHIHRHTHUHYIDISITJAJWKAKKKMKNKOLALBLNLOLTLVMGMIMKMLMNMRMSMTMYNENLNNNOOCPAPLPSPTRORUSASDSISKSLSNSOSQSRSUSVSWTATETGTHTKTLTRTTUKURUZVIYIYOZHr)r LANGUAGE_MAPrL/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/fal/stt.pylanguage_to_fal_languagest       !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVerc@seZdZdZdS)FalSTTSettingszSettings for FalSTTService.N)__name__ __module__ __qualname____doc__rrrrrsrcseZdZUdZeZeed<GdddeZdddddddde d d e e d e e j d e d e de de ede ede ede effddZdefddZdede e fddZe d"de dede e fddZdedeedffd d!ZZS)# FalSTTServicezSpeech-to-text service using Fal's Wizper API. This service uses Fal's Wizper API to perform speech-to-text transcription on audio segments. It inherits from SegmentedSTTService to handle audio buffering and speech detection. _settingsc@sHeZdZUdZejZeeed<dZ e ed<dZ e ed<dZ e ed<d S) zFalSTTService.InputParamsaConfiguration parameters for Fal's Wizper API. .. deprecated:: 0.0.105 Use ``settings=FalSTTService.Settings(...)`` instead. Parameters: language: Language of the audio input. Defaults to English. task: Task to perform ('transcribe' or 'translate'). Defaults to 'transcribe'. chunk_level: Level of chunking ('segment'). Defaults to 'segment'. version: Version of Wizper model to use. Defaults to '3'. r transcribetasksegment chunk_level3versionN) rrrrr rrr__annotations__rstrrrrrrr InputParamss   rNrrr) api_keyaiohttp_sessionrrr sample_rateparamssettingsttfs_p99_latencyrrrrrrrrrc  s|jdtjd} |dur4|d|s4|jdur|j| _|jdkr$|j}|jdkr,|j}|jdkr4|j}|dur=| |t j d || | d| ||_ ||_ ||_ |pZtdd |_|jsctd ||_|du|_dS) apInitialize 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=FalSTTService.Settings(...)`` 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)Settingsr r"_warn_init_param_moved_to_settingsrrrr apply_updatesuper__init___task _chunk_level_versionosgetenv_api_key ValueError_session _owns_session) selfrrrrrrrrrkwargsdefault_settings __class__rrrsD&      zFalSTTService.__init__rcCsdS)zCheck if the service can generate processing metrics. Returns: True, as Fal STT service supports metrics generation. Tr)rrrrcan_generate_metricssz"FalSTTService.can_generate_metricsrcCst|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)rrrrrlanguage_to_service_language s z*FalSTTService.language_to_service_language transcriptis_finalcs|IdHdS)z+Handle a transcription result with tracing.N)stop_processing_metrics)rr r rrrr_handle_transcriptionsz#FalSTTService._handle_transcriptionaudioc Csz|IdH|jst|_dt|}d|i}|jjdur+|jj|d<|j dur5|j |d<|j dur?|j |d<|j durI|j |d<d|j d d }|jj d ||d 4IdH8}|jd kr|IdH}td|jd|dV WdIdHWdS|IdH}WdIdHn 1IdHswY|rd|vr|d}|r||d|jjIdHtd|dt||jtt|jj|dVWdSWdSWdSWdSty} ztd| dVWYd} ~ dSd} ~ ww)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 b64encodedecoderrrrrrpoststatusrrrstripr rdebugr _user_idrr Exception) rrdata_uripayloadrresp error_textresponsererrrrun_sttsb             (    zFalSTTService.run_stt)N)rrrrrrrrrr rrrrintfloatrboolrr r rr bytesrrr* __classcell__rrrrrsZ    R  "r)"rrr dataclassesrtypingrrrlogururpydanticrpipecat.frames.framesrrr pipecat.services.settingsr pipecat.services.stt_latencyr pipecat.services.stt_servicer pipecat.transcriptions.languager rpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsrrrrrrrrrs&        q