o i, @sRdZddlZddlmZddlmZmZmZddlm Z ddl m Z m Z m Z mZmZmZmZddlmZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZzddl m!Z!m"Z"m#Z#m$Z$ddl%m&Z&m'Z'ddl(m)Z)Wn e*yZ+ze ,de+e ,de-de+dZ+[+wweGdddeZ.GdddeZ/dS)zAzure Speech-to-Text service implementation for Pipecat. This module provides speech-to-text functionality using Azure Cognitive Services Speech SDK for real-time audio transcription. N) dataclass)AnyAsyncGeneratorOptional)logger) CancelFrameEndFrame ErrorFrameFrameInterimTranscriptionFrame StartFrameTranscriptionFramelanguage_to_azure_language) STTSettings)AZURE_TTFS_P99) STTService)Language)time_now_iso8601) traced_stt)CancellationReason ResultReason SpeechConfigSpeechRecognizer)AudioStreamFormatPushAudioInputStream) AudioConfigz Exception: zCIn order to use Azure, you need to `pip install pipecat-ai[azure]`.zMissing module: c@seZdZdZdS)AzureSTTSettingszSettings for AzureSTTService.N)__name__ __module__ __qualname____doc__r"r"N/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/azure/stt.pyr6srcs\eZdZUdZeZeed<dejdddde dde de e de ede e d e e d e e d e ed e e ffd dZdefddZdede e fddZdedee efffdd ZdedeedffddZdeffdd Zdeffdd Zdeffdd Zd!d"Z d#d$Z!e" d/d%e d&ede efd'd(Z#d)d*Z$d+d,Z%d-d.Z&Z'S)0AzureSTTServicea"Azure Speech-to-Text service for real-time audio transcription. This service uses Azure Cognitive Services Speech SDK to convert speech audio into text transcriptions. It supports continuous recognition and provides real-time transcription results with timing information. _settingsN)regionlanguage sample_rateprivate_endpoint endpoint_idsettingsttfs_p99_latencyapi_keyr&r'r(r)r*r+r,c  s|jdtjd} |dur|tjkr|dd|| _|dur#| |tjd ||| d| | jp7ttj} |s@|s@t d|rR|rIt dt ||| d|_ nt ||| d|_ |r`||j _d|_d|_dS) aInitialize the Azure STT service. Args: api_key: Azure Cognitive Services subscription key. region: Azure region for the Speech service (e.g., 'eastus'). Required unless ``private_endpoint`` is provided. language: Language for speech recognition. Defaults to English (US). .. deprecated:: 0.0.105 Use ``settings=AzureSTTService.Settings(language=...)`` instead. sample_rate: Audio sample rate in Hz. If None, uses service default. private_endpoint: Private endpoint for STT behind firewall. See https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-private-link?tabs=portal endpoint_id: Custom model endpoint id. 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. N)modelr'r')r(r,r+z7Either 'region' or 'private_endpoint' must be provided.zHBoth 'region' and 'private_endpoint' provided; 'region' will be ignored.) subscriptionendpointspeech_recognition_language)r/r&r1r")SettingsrEN_US"_warn_init_param_moved_to_settingsr' apply_updatesuper__init__r ValueErrorrwarningr_speech_configr* _audio_stream_speech_recognizer) selfr-r&r'r(r)r*r+r,kwargsdefault_settingsrecognition_language __class__r"r#r7HsP#    zAzureSTTService.__init__returncCsdS)zCheck if this service can generate performance metrics. Returns: True as this service supports metrics generation. Tr"r=r"r"r#can_generate_metricssz$AzureSTTService.can_generate_metricscCst|S)zConvert a Language enum to Azure service-specific language code. Args: language: The language to convert. Returns: The Azure-specific language identifier, or None if not supported. r)r=r'r"r"r#language_to_service_languages z,AzureSTTService.language_to_service_languagedeltacsXt|IdH}d|vr*|jjpttj|j_|j r*| IdH| IdH|S)z9Apply a settings delta and reconnect if language changed.Nr') r6_update_settingsr%r'rrr3r:r1r; _disconnect_connect)r=rGchangedrAr"r#rHsz AzureSTTService._update_settingsaudioc Cshz|IdH|jr|j|dVWdSty3}ztd|dVWYd}~dSd}~ww)aoProcess audio data for speech-to-text conversion. Feeds audio data to the Azure speech recognizer for processing. Recognition results are handled asynchronously through callbacks. Args: audio: Raw audio bytes to process. Yields: Frame: Either None for successful processing or ErrorFrame on failure. NzUnknown error occurred: )error)start_processing_metricsr;write Exceptionr )r=rLer"r"r#run_stts    zAzureSTTService.run_sttframec&t|IdH|IdHdS)zzStart the speech recognition service. Args: frame: Frame indicating the start of processing. N)r6startrJr=rSrAr"r#rUzAzureSTTService.startcrT)zwStop the speech recognition service. Args: frame: Frame indicating the end of processing. N)r6stoprIrVrAr"r#rXrWzAzureSTTService.stopcrT)zpCancel the speech recognition service. Args: frame: Frame indicating cancellation. N)r6cancelrIrVrAr"r#rYrWzAzureSTTService.cancelc s|jrdSz:t|jdd}t||_t|jd}t|j|d|_|jj |j |jj |j |jj |j|jWdSty`}z|jd||dIdHWYd}~dSd}~ww)zHInitialize the Azure speech recognizer and begin continuous recognition.N)samples_per_secondchannels)stream) speech_config audio_configz*Uncaught exception during initialization: ) error_msg exception)r;rr(rrrr:r< recognizingconnect_on_handle_recognizing recognized_on_handle_recognizedcanceled_on_handle_canceled"start_continuous_recognition_asyncrP push_error)r= stream_formatr_rQr"r"r#rJs(   zAzureSTTService._connectcs6|jr |jd|_|jr|jd|_dSdS)z)Stop recognition and close audio streams.N)r<!stop_continuous_recognition_asyncr;closerDr"r"r#rIs   zAzureSTTService._disconnect transcriptis_finalcs|IdHdS)z+Handle a transcription result with tracing.N)stop_processing_metrics)r=rnror'r"r"r#_handle_transcriptionsz%AzureSTTService._handle_transcriptioncCs|jjtjkrCt|jjdkrEt|jddp|jj}t |jj|j t ||d}t ||jjd||t |||dSdSdS)Nrr'resultT)rsreasonrRecognizedSpeechlentextgetattrr%r'r _user_idrasynciorun_coroutine_threadsaferqget_event_loop push_framer=eventr'rSr"r"r#rfsz%AzureSTTService._on_handle_recognizedcCsp|jjtjkr4t|jjdkr6t|jddp|jj}t |jj|j t ||d}t |||dSdSdS)Nrr'rr)rsrtrRecognizingSpeechrvrwrxr%r'r ryrrzr{r}r|r~r"r"r#rd'sz&AzureSTTService._on_handle_recognizingcCsV|jj}|jtjkr)d|j}|jr|d|j7}t|j|d| dSdS)Nz Azure STT recognition canceled: z - )r`) rscancellation_detailsrtrError error_detailsrzr{rjr|)r=rdetailsr`r"r"r#rh3s  z#AzureSTTService._on_handle_canceled)N)(rrr r!rr2__annotations__rr3rstrrintfloatr7boolrErFrdictrrHbytesrr rRr rUrrXrrYrJrIrrqrfrdrh __classcell__r"r"rAr#r$=sb   X       r$)0r!rz dataclassesrtypingrrrlogururpipecat.frames.framesrrr r r r r pipecat.services.azure.commonrpipecat.services.settingsrpipecat.services.stt_latencyrpipecat.services.stt_servicerpipecat.transcriptions.languagerpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsrazure.cognitiveservices.speechrrrr$azure.cognitiveservices.speech.audiorr%azure.cognitiveservices.speech.dialogrModuleNotFoundErrorrQrMrPrr$r"r"r"r#s4  $