o iS @sZdZddlZddlZddlZddlZddlmZddlmZm Z m Z ddl m Z ddl mZmZmZmZmZmZmZddlmZmZmZddlmZdd lmZdd lmZdd lm Z m!Z!dd l"m#Z#dd l$m%Z%zddl&m'Z(ddl)m*Z*Wn e+yZ,ze -de,e -de.de,dZ,[,wweGdddeZ/GdddeZ0dS)zAWS Transcribe Speech-to-Text service implementation. This module provides a WebSocket-based connection to AWS Transcribe for real-time speech-to-text transcription with support for multiple languages and audio formats. N) dataclass)AnyAsyncGeneratorOptional)logger) CancelFrameEndFrame ErrorFrameFrameInterimTranscriptionFrame StartFrameTranscriptionFrame)build_event_message decode_eventget_presigned_url) STTSettings)AWS_TRANSCRIBE_TTFS_P99)WebsocketSTTService)Languageresolve_language)time_now_iso8601) traced_stt)connect)Statez Exception: zHIn order to use AWS services, you need to `pip install pipecat-ai[aws]`.zMissing module: c@seZdZdZdS)AWSTranscribeSTTSettingsz%Settings for AWSTranscribeSTTService.N)__name__ __module__ __qualname____doc__rrL/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/aws/stt.pyr0srcseZdZUdZeZeed<dddddddeddee dee dee dee d ee d ee d eed ee ffd dZ defddZde de fddZdedee efffdd Zdeffdd Zdeffdd Zdeffdd Zdedeedffd d!Zfd"d#Zfd$d%Z d&d'Z!d(d)Z"d e de dBfd*d+Z#e$ d4d,e d-ed ee fd.d/Z%d0d1Z&d2d3Z'Z(S)5AWSTranscribeSTTServicea AWS Transcribe Speech-to-Text service using WebSocket streaming. Provides real-time speech transcription using AWS Transcribe's streaming API. Supports multiple languages, configurable sample rates, and both interim and final transcription results. _settingsN)api_keyaws_access_key_idaws_session_tokenregion sample_ratelanguagesettingsttfs_p99_latencyr#r$r%r&r'r(r)r*c  s|jdtjd} |dur|dd|| _|dur| |tjd||| d| d|_d|_ d|_ d|_ |p=t d|pCt d |pIt d |pPt d d d |_d|_dS)aInitialize the AWS Transcribe STT service. Args: api_key: AWS secret access key. If None, uses AWS_SECRET_ACCESS_KEY environment variable. aws_access_key_id: AWS access key ID. If None, uses AWS_ACCESS_KEY_ID environment variable. aws_session_token: AWS session token for temporary credentials. If None, uses AWS_SESSION_TOKEN environment variable. region: AWS region for the service. sample_rate: Audio sample rate in Hz. If None, uses the pipeline sample rate. AWS Transcribe only supports 8000 or 16000 Hz; other values are clamped to 16000 Hz at connect time. language: Language for transcription. .. deprecated:: 0.0.105 Use ``settings=AWSTranscribeSTTService.Settings(language=...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark **kwargs: Additional arguments passed to parent STTService class. N)modelr(r()r'r*r)linear16FAWS_ACCESS_KEY_IDAWS_SECRET_ACCESS_KEYAWS_SESSION_TOKEN AWS_REGIONz us-east-1)r$aws_secret_access_keyr%r&r)SettingsrEN"_warn_init_param_moved_to_settingsr( apply_updatesuper__init___media_encoding_number_of_channels_show_speaker_label_enable_channel_identificationosgetenv _credentials _receive_task) selfr#r$r%r&r'r(r)r*kwargsdefault_settings __class__rr r8Bs4#      z AWSTranscribeSTTService.__init__returncCsdS)zCheck if this service can generate processing metrics. Returns: True, as AWS Transcribe STT supports metrics generation. TrrArrr can_generate_metricssz,AWSTranscribeSTTService.can_generate_metricsencodingcCsddi}|||S)zConvert internal encoding format to AWS Transcribe format. Args: encoding: Internal encoding format string. Returns: AWS Transcribe compatible encoding format. r,pcm)get)rArI encoding_maprrr get_service_encodings  z,AWSTranscribeSTTService.get_service_encodingdeltacs>t|IdH}|r|jr|IdH|IdH|S)z9Apply a settings delta and reconnect if anything changed.N)r7_update_settings _websocket _disconnect_connect)rArNchangedrDrr rOs  z(AWSTranscribeSTTService._update_settingsframec&t|IdH|IdHdS)zInitialize the connection when the service starts. Args: frame: Start frame signaling service initialization. N)r7startrRrArTrDrr rVzAWSTranscribeSTTService.startcrU)zStop the service and disconnect from AWS Transcribe. Args: frame: End frame signaling service shutdown. N)r7stoprQrWrDrr rYrXzAWSTranscribeSTTService.stopcrU)zCancel the service and disconnect from AWS Transcribe. Args: frame: Cancel frame signaling service cancellation. N)r7cancelrQrWrDrr rZrXzAWSTranscribeSTTService.cancelaudioc Cs|jr=|jjtjur=zt|}|j|IdH|IdHWnty<}ztd|dVWYd}~nd}~wwdVdS)zProcess audio data and send to AWS Transcribe. Args: audio: Raw audio bytes to transcribe. Yields: ErrorFrame: If processing fails or connection issues occur. NzError sending audio: )error) rPstaterOPENrsendstart_processing_metrics Exceptionr )rAr[ event_messageerrr run_stts  zAWSTranscribeSTTService.run_sttcsLtIdH|IdH|jr"|js$|||j|_dSdSdS)zrConnect to the AWS Transcribe service. Establishes websocket connection and starts receive task. N)r7rR_connect_websocketrPr@ create_task_receive_task_handler _report_errorrGrDrr rRs  z AWSTranscribeSTTService._connectc stIdH|jr||jIdHd|_|jrU|jjtjurUzddd}|jt |IdHWnt yT}z|j d||dIdHWYd}~nd}~ww| IdHdS)zeDisconnect from the AWS Transcribe service. Sends end-stream message and cleans up. Neventend)z message-typerizError sending end-stream:  error_msg exception)r7rQr@ cancel_taskrPr]rr^r_jsondumpsra push_error_disconnect_websocket)rA end_streamrcrDrr rQs &z#AWSTranscribeSTTService._disconnectc svz|jr|jjtjurWdStd|jj}|s!td||j }|dvr3t d|dd}d t j tjtjtjd d }d |d d d}t|jd|jd|jd|jdd|||j||jdd|j|jd }t|d|dddt||dgddddIdH|_|dIdHt|dWdSty}z|jd||dIdHd}~ww) z5Establish the websocket connection to AWS Transcribe.Nz&Connecting to AWS Transcribe WebSocketzUnsupported language: )i@>zOAWS Transcribe only supports 8000 Hz or 16000 Hz sample rates. Converting from z Hz to 16000 Hz.rt)kzhttps://localhost13z keep-alive)OriginzSec-WebSocket-KeyzSec-WebSocket-Version Connectionr&r$r2r%) access_key secret_key session_tokenThigh) r& credentials language_codemedia_encodingr'number_of_channels$enable_partial_results_stabilizationpartial_results_stabilityshow_speaker_labelenable_channel_identificationz# Connecting to WebSocket with URL: dz...mqtt)additional_headers subprotocols ping_interval ping_timeout compression on_connectedz) Successfully connected to AWS Transcribez%Unable to connect to AWS Transcribe: rk)rPr]rr^rdebugr"r( ValueErrorr'warningjoinrandomchoicesstringascii_uppercaseascii_lowercasedigitsrr?rMr9r:r;r<websocket_connect_call_event_handlerinforarq)rArconnect_sample_rate websocket_keyr presigned_urlrcrrr resz    z*AWSTranscribeSTTService._connect_websocketc szNz|jrtd|jIdHWnty3}z|jd||dIdHWYd}~nd}~wwWd|_|dIdHdSWd|_|dIdHdSd|_|dIdHw)z1Close the websocket connection to AWS Transcribe.z+Disconnecting from AWS Transcribe WebSocketNzError closing websocket: rkon_disconnected)rPrrcloserarqr)rArcrrr rrJs$ &z-AWSTranscribeSTTService._disconnect_websocketcCsitjdtjdtjdtjdtjdtjdtjdtjdtj dtj dtj dtj dtj dtjdtjd tjd tjd itjd tjd tjd tjd tjd tjd tjdtjdtjdtjdtjdtjdtjd tjdtj dtj!dtj"ditj#dtj$dtj%dtj&dtj'dtj(dtj)dtj*dtj+dtj,dtj-dtj.dtj/dtj0dtj1dtj2dtj3ditj4dtj5d tj6d tj7d!tj8d!tj9d"tj:d"tj;d#tjd$tj?d%tj@d%tjAd%tjBd&tjCd&tjDd'itjEd'tjFd(tjGd)tjHd)tjId*tjJd*tjKd+tjLd+tjMd,tjNd,tjOd-tjPd-tjQd.tjRd.tjSd/tjTd0tjUd0tjVd1tjWd1tjXd1tjYd2tjZd2tj[d3tj\d3tj]d4tj^d4tj_d5tj`d5i }ta||d6d7S)8aConvert internal language enum to AWS Transcribe language code. Source: https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html All language codes that support streaming are included. Args: language: Internal language enumeration value. Returns: AWS Transcribe compatible language code, or None if unsupported. zaf-ZAzar-SAzar-AEzeu-ESzca-ESzzh-CNzzh-TWzzh-HKzhr-HRzcs-CZzda-DKznl-NLzen-USzen-AUzen-GBzen-INzen-IEzen-NZzen-ZAzfa-IRzfi-FIzfr-FRzfr-CAzgl-ESzka-GEzde-DEzde-CHzel-GRzhe-ILzhi-INzid-IDzit-ITzja-JPzko-KRzlv-LVzms-MYzno-NOzpl-PLzpt-PTzpt-BRzro-ROzru-RUzsr-RSzsk-SKzso-SOzes-ESzes-USzsv-SEztl-PHzth-THzuk-UAzvi-VNzzu-ZAF) use_base_code)brAFAF_ZAARAR_AEAR_SAEUEU_ESCACA_ESZHZH_CNZH_TWZH_HKYUEHRHR_HRCSCS_CZDADA_DKNLNL_NLr4EN_AUEN_GBEN_INEN_IEEN_NZEN_ZAEN_USFAFA_IRFIFI_FIFRFR_FRFR_CAGLGL_ESKAKA_GEDEDE_DEDE_CHELEL_GRHEHE_ILHIHI_INIDID_IDITIT_ITJAJA_JPKOKO_KRLVLV_LVMSMS_MYNBNB_NONOPLPL_PLPTPT_PTPT_BRRORO_RORURU_RUSRSR_RSSKSK_SKSOSO_SOESES_ESES_USSVSV_SETLFILFIL_PHTHTH_THUKUK_UAVIVI_VNZUZU_ZAr)rAr( LANGUAGE_MAPrrr language_to_service_languageVst     !"#$%&()+,./1235689;<=?@BCEFHIKLNOQRTUWXZ[\^_abcefhiklnoqrtuvxy{ z4AWSTranscribeSTTService.language_to_service_language transcriptis_finalcsdSNr)rArrr(rrr _handle_transcriptionsz-AWSTranscribeSTTService._handle_transcriptioncCs|jr|jStd)zGet the current WebSocket connection. Returns: The WebSocket connection. Raises: Exception: If WebSocket is not connected. zWebsocket not connected)rPrarGrrr _get_websockets z&AWSTranscribeSTTService._get_websocketc s|2z3dHW}zt|\}}|ddkr|didg}|r~|d}|dg}|r~|ddd}|d d  }|r~|rk|t||jt|jj|d IdH| |||jjIdH| IdHnB|t ||jt|jj|d IdHn.|dd kr|d d} |j d| dIdHnt |d|t |d|Wqty} zt d| WYd} ~ qd} ~ ww6dS)zxReceive and process websocket messages. Continuously processes messages from the websocket connection. Nz :message-typeri TranscriptResultsr Alternativesru IsPartialT)resultrmMessagez Unknown errorzAWS Transcribe error: )rlz Other message type received: z Payload: zError processing message: )rrrK push_framer _user_idrr"r(rstop_processing_metricsr rqrrrar) rAresponseheaderspayloadresultsr  alternativesrrrlrcrrr _receive_messagessd       z)AWSTranscribeSTTService._receive_messagesr))rrrrrr3__annotations__rrstrintrfloatr8boolrHrMrdictrrOr rVrrYrrZbytesrr rdrRrQrerrrrrrr __classcell__rrrDr r!7sj   I     L   r!)1rror=rr dataclassesrtypingrrrlogururpipecat.frames.framesrrr r r r r pipecat.services.aws.utilsrrrpipecat.services.settingsrpipecat.services.stt_latencyrpipecat.services.stt_servicerpipecat.transcriptions.languagerrpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsrwebsockets.asyncio.clientrrwebsockets.protocolrModuleNotFoundErrorrcr\rarr!rrrr s8  $