o iw @sUdZddlZddlmZmZddlmZmZmZm Z m Z ddl m Z ddl mZddlmZmZmZmZmZmZmZmZmZmZddlmZdd lmZdd lmZm Z m!Z!m"Z"dd l#m$Z$dd l%m&Z&dd l'm(Z(m)Z)ddl*m+Z+ddl,m-Z-zddl.m/Z/ddl0m1Z1ddl2m3Z3Wn e4yZ5ze 6de5e 6de7de5dZ5[5wwde(de8fddZ9eddGdddZ:e:dddddddd e:dddddddd e:ddddd!ddd d"Z;ee8e:fedS)(a'Sarvam AI Speech-to-Text service implementation. This module provides a streaming Speech-to-Text service using Sarvam AI's WebSocket-based API. It supports real-time transcription with Voice Activity Detection (VAD) and can handle multiple audio formats for Indian language speech recognition. N) dataclassfield)AnyAsyncGeneratorDictLiteralOptional)logger) BaseModel) CancelFrameEndFrame ErrorFrameFrame StartFrameTranscriptionFrameUserStartedSpeakingFrameUserStoppedSpeakingFrameVADUserStartedSpeakingFrameVADUserStoppedSpeakingFrame)FrameDirection) sdk_headers) NOT_GIVEN STTSettings _NotGivenis_given)SARVAM_TTFS_P99) STTService)Languageresolve_language)time_now_iso8601) traced_stt) AsyncSarvamAI)ApiError) EventTypez Exception: zEIn order to use Sarvam, you need to `pip install pipecat-ai[sarvam]`.zMissing module: languagereturncCsZtjdtjdtjdtjdtjdtjdtjdtjdtj d tj d tj d tj d i }t ||d dS)zConvert a Language enum to Sarvam's language code format. Args: language: The Language enum value to convert. Returns: The Sarvam language code string. bn-INgu-INhi-INkn-INml-INmr-INta-INte-INpa-INod-INen-INas-INF) use_base_code)rBN_INGU_INHI_INKN_INML_INMR_INTA_INTE_INPA_INOR_INEN_INAS_INr)r$ LANGUAGE_MAPr@O/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/sarvam/stt.pylanguage_to_sarvam_language9s rBT)frozenc@sReZdZUdZeed<eed<eed<eeed<eeed<eed<eed<d S) ModelConfigaKImmutable configuration for a Sarvam STT model. Attributes: supports_prompt: Whether the model accepts prompt parameter. supports_mode: Whether the model accepts mode parameter. supports_language: Whether the model accepts language parameter. default_language: Default language code (None = auto-detect). default_mode: Default mode (None = not applicable). use_translate_endpoint: Whether to use speech_to_text_translate_streaming endpoint. use_translate_method: Whether to use translate() method instead of transcribe(). supports_prompt supports_modesupports_languagedefault_language default_modeuse_translate_endpointuse_translate_methodN)__name__ __module__ __qualname____doc__bool__annotations__rstrr@r@r@rArDUs     rDFunknown)rErFrGrHrIrJrK transcribe) saarika:v2.5z saaras:v2.5z saaras:v3 MODEL_CONFIGSc@sleZdZUdZedddZedBeBed<edddZ e dBeBed<ed ddZ e dBeBed <dS) SarvamSTTSettingsaFSettings for SarvamSTTService. Parameters: prompt: Optional prompt to guide transcription/translation style/context. Only applicable to models that support prompts (e.g., saaras:v2.5). vad_signals: Enable VAD signals in response. high_vad_sensitivity: Enable high VAD sensitivity. cCtSNrr@r@r@rAzSarvamSTTSettings.)default_factoryNpromptcCrXrYrZr@r@r@rAr[r\ vad_signalscCrXrYrZr@r@r@rAr[r\high_vad_sensitivity) rLrMrNrOrr^rRrrQr_rPr`r@r@r@rArWs  "rWcseZdZUdZeZeed<GdddeZdddddde ddd d e d e e d e e d d e e de de ede ede ede edeffddZdede fddZde e fddZdefddZdedeffd d! Zd"edee efffd#d$ Zd%e e fd&d'Zdeffd(d) Zdeffd*d+ Z de!ffd,d- Z"d.e#de$edffd/d0Z%d1d2Z&d3d4Z'd5d6Z(d7d8Z)e* dGd9e d:ede efd;d<Z+d=e defd>d?Z,defd@dAZ-dBe#fdCdDZ.dEdFZ/Z0S)HSarvamSTTServiceaSarvam speech-to-text service. Provides real-time speech recognition using Sarvam's WebSocket API. Event handlers available (in addition to STTService events): - on_connected(service): Connected to Sarvam WebSocket - on_disconnected(service): Disconnected from Sarvam WebSocket - on_connection_error(service, error): Connection error occurred Example:: @stt.event_handler("on_connected") async def on_connected(service): ... _settingsc@sfeZdZUdZdZeeed<dZee ed<dZ ee ded<dZ ee ed<dZee ed<dS) zSarvamSTTService.InputParamsaConfiguration parameters for Sarvam STT service. .. deprecated:: 0.0.105 Use ``settings=SarvamSTTService.Settings(...)`` instead. Parameters: language: Target language for transcription. - saarika:v2.5: Defaults to "unknown" (auto-detect supported) - saaras:v2.5: Not used (auto-detects language) - saaras:v3: Defaults to "unknown" (auto-detect supported) prompt: Optional prompt to guide transcription/translation style/context. Only applicable to saaras:v2.5. Defaults to None. mode: Mode of operation for saaras:v3 models only. Options: transcribe, translate, verbatim, translit, codemix. Defaults to "transcribe" for saaras:v3. vad_signals: Enable VAD signals in response. Defaults to None. high_vad_sensitivity: Enable high VAD (Voice Activity Detection) sensitivity. Defaults to None. Nr$r^rT translateverbatimtranslitcodemixmoder_r`)rLrMrNrOr$rrrQr^rRrhrr_rPr`r@r@r@rA InputParamss riNwavg@) modelrh sample_rateinput_audio_codecparamssettingsttfs_p99_latencykeepalive_timeoutkeepalive_intervalapi_keyrkrhrcrlrmrnrorprqrrc  s|jdddddd} |dur|dd|| _|dur:|d|s:|j| _|j| _|jdur2|j}|j| _|j| _|durC| || j} | t vr^d t t }t d| d|d t | |_| jdurt|jjstt d | d |dur|jjst d | d | jdur|jjst d | d |dur|jj}tjd||| | | d| ||_||_||_t|_t||jd|_d|_d|_d|_| jr|d|d|dt !d|jdS)aInitialize the Sarvam STT service. Args: api_key: Sarvam API key for authentication. model: Sarvam model to use for transcription. .. deprecated:: 0.0.105 Use ``settings=SarvamSTTService.Settings(model=...)`` instead. mode: Mode of operation. Options: transcribe, translate, verbatim, translit, codemix. Only applicable to models that support it (e.g., saaras:v3). Defaults to the model's default mode. sample_rate: Audio sample rate. Defaults to 16000 if not specified. input_audio_codec: Audio codec/format of the input file. Defaults to "wav". params: Configuration parameters for Sarvam STT service. .. deprecated:: 0.0.105 Use ``settings=SarvamSTTService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark keepalive_timeout: Seconds of no audio before sending silence to keep the connection alive. None disables keepalive. keepalive_interval: Seconds between idle checks when keepalive is enabled. **kwargs: Additional arguments passed to the parent STTService. rUN)rkr$r^r_r`rkrnz, zUnsupported model 'z'. Allowed values: .Model '$' does not support prompt parameter.z"' does not support mode parameter.>' does not support language parameter (auto-detects language).)rlrprqrrro)api_subscription_keyheaderson_speech_startedon_speech_stoppedon_utterance_endz)Sarvam STT initialized with SDK headers: r@)"Settings"_warn_init_param_moved_to_settingsrkr$r^rhr_r` apply_updaterVjoinsortedkeys ValueError_configrErFrGrIsuper__init___api_key_mode_input_audio_codecr _sdk_headersr!_sarvam_client_websocket_context_socket_client _receive_task_register_event_handlerr info)selfrsrkrhrlrmrnrorprqrrkwargsdefault_settingsresolved_modelallowed __class__r@rArst.          zSarvamSTTService.__init__r$r%cCst|S)zConvert pipecat Language enum to Sarvam's language code. Args: language: The Language enum value to convert. Returns: The Sarvam language code string. )rB)rr$r@r@rAlanguage_to_service_languageKs z-SarvamSTTService.language_to_service_languagecCs|jjr t|jjS|jjS)zFResolve the current language setting to a Sarvam language code string.)rbr$rBrrHrr@r@rA_get_language_stringVs z%SarvamSTTService._get_language_stringcCsdS)zCheck if this service can generate processing metrics. Returns: True, as Sarvam service supports metrics generation. Tr@rr@r@rAcan_generate_metrics\sz%SarvamSTTService.can_generate_metricsframe directioncsjt||IdH|jjs/t|tr|IdHdSt|tr1|jr3|j IdHdSdSdSdS)zProcess incoming frames. Handles VAD frames for TTFB tracking when using Pipecat's VAD instead of Sarvam's built-in VAD. N) r process_framerbr_ isinstancer_start_metricsrrflush)rrrrr@rArds  zSarvamSTTService.process_framedeltacst|jr|jdur|jjstd|jjdt||jr7t|j r7|j dur7|jj s7td|jjdt |IdH}ddh| @rX|IdH|IdHfdd|D}|rj|||S) a^Apply a settings delta, validate, sync state, and reconnect. Args: delta: A :class:`STTSettings` (or ``SarvamSTTService.Settings``) delta. Returns: Dict mapping changed field names to their previous values. Raises: ValueError: If a setting is not supported by the current model. Nrurwrvr$r^csi|] \}}|vr||qSr@r@.0kvreconnect_fieldsr@rA z5SarvamSTTService._update_settings..)rr$rrGrrbrkrr}r^rEr_update_settingsr _disconnect_connectitems _warn_unhandled_updated_settings)rrchanged unhandledrrrArts(    z!SarvamSTTService._update_settingsr^csddl}||d|j|jjdtddWdn1s&wY|jjs?|dur=t d|j j ddSt d |j j d ||j _|IdH|IdHdS) aSet the transcription/translation prompt and reconnect. .. deprecated:: 0.0.104 Use ``STTUpdateSettingsFrame(SarvamSTTService.Settings(prompt=...))`` instead. Args: prompt: Prompt text to guide transcription/translation style/context. Pass None to clear/disable prompt. Only applicable to models that support prompts. rNalwaysz[.set_prompt() is deprecated. Use STTUpdateSettingsFrame(self.Settings(prompt=...)) instead.) stacklevelrurvz Updating z prompt.)warningscatch_warnings simplefilterwarnrrLDeprecationWarningrrErrbrkr rr^rr)rr^rr@r@rA set_prompts(    zSarvamSTTService.set_promptc&t|IdH|IdHdS)z~Start the Sarvam STT service. Args: frame: The start frame containing initialization parameters. N)rstartrrrrr@rArzSarvamSTTService.startcr)zVStop the Sarvam STT service. Args: frame: The end frame. N)rstoprrrr@rArrzSarvamSTTService.stopcr)z[Cancel the Sarvam STT service. Args: frame: The cancel frame. N)rcancelrrrr@rArrzSarvamSTTService.cancelaudioc Cs|js dVdSz=t|d}|jdr|jnd|j}|||jd}|jjr9|jj di|IdHn |jj di|IdHWnt yb}zt d||dVWYd}~nd}~wwdVdS)zSend audio data to Sarvam for transcription. Args: audio: Raw audio bytes to transcribe. Yields: Frame: None (transcription results come via WebSocket callbacks). Nutf-8audio/rencodingrlzError sending audio to Sarvam: )error exceptionr@) rbase64 b64encodedecoder startswithrlrrKrdrT Exceptionr )rr audio_base64r method_kwargser@r@rArun_stts.     zSarvamSTTService.run_sttc s6tdzȈjjtjd}jjsd|d<jjdur)jjr%dnd|d<jjdur9jjr5dnd|d<}|durE||d <j j rSj durSj |d <jj durcj j rcjj |d <fd d }j jrz|jjjfi|_n |jjjfi|_jIdH_jj durj j rtjdd}t|r|jj IdHfdd}jtj|_tdWdSt y}zd_d_j!d||dIdHWYd}~dSd}~wt"y}zd_d_j!d||dIdHWYd}~dSd}~ww)z.Connect to Sarvam WebSocket API using the SDK.zConnecting to Sarvam)rkrltrue flush_signalNfalser_r` language_coderhr^c sdji}|g}d|vr|dd|Dd}|D]C}z|di|d|iWSty@}z|}WYd}~nd}~wwz |di|WSty_}z|}WYd}~qd}~ww|durf||di|S)Nadditional_headersr^cSsi|] \}}|dkr||qS)r^r@rr@r@rAr1rzPSarvamSTTService._connect.._connect_with_sdk_headers..request_optionsr@)rappendr TypeError) connect_fnrrattemptslast_type_errorattempt_kwargsrrr@rA_connect_with_sdk_headers)s2 z._connect_with_sdk_headersrcs|dS)z)Wrapper to handle async response handler.N) create_task_handle_message)messagerr@rA_message_handler\sz3SarvamSTTService._connect.._message_handlerz Connected to Sarvam successfullyzSarvam API error:  error_msgrzFailed to connect to Sarvam: )#r debugrbrkrRrlr_r`rrrFrr^rErJr"speech_to_text_translate_streamingconnectrspeech_to_text_streaming __aenter__rgetattrcallableonr#MESSAGEr_receive_task_handlerr_create_keepalive_taskrr" push_errorr)rconnect_kwargslanguage_stringr prompt_setterrrr@rrArsj        ((zSarvamSTTService._connectc s|IdH|jr||jIdHd|_|j}|j}d|_d|_|rj|rlzget)rrmappingr@r@rArsz+SarvamSTTService._map_language_code_to_enumcCs |jduS)z6Check if the Sarvam SDK websocket client is connected.N)rrr@r@rA_is_keepalive_readys z$SarvamSTTService._is_keepalive_readysilencecs~t|d}|jdr|jnd|j}|||jd}|jjr1|jj di|IdHdS|jj di|IdHdS)zSend silent audio via the Sarvam SDK to keep the connection alive. Args: silence: Silent 16-bit mono PCM audio bytes. rrrNr@) rrrrrrlrrKrrdrT)rrrrrr@r@rA_send_keepalives  z SarvamSTTService._send_keepalivecs|IdHdS)z$Start processing metrics collection.N)start_processing_metricsrr@r@rArszSarvamSTTService._start_metricsrY)1rLrMrNrOrWr}rQr rirrRrrintfloatrrrrrPrrrrrrrrrrrr rr rbytesrrrrrrr rrrrr __classcell__r@r@rrAras       '#   *p@  ra)?rOr dataclassesrrtypingrrrrrlogurur pydanticr pipecat.frames.framesr r r rrrrrrr"pipecat.processors.frame_processorrpipecat.services.sarvam._sdkrpipecat.services.settingsrrrrpipecat.services.stt_latencyrpipecat.services.stt_servicerpipecat.transcriptions.languagerrpipecat.utils.timer(pipecat.utils.tracing.service_decoratorsr sarvamair!sarvamai.core.api_errorr"sarvamai.core.eventsr#ModuleNotFoundErrorrrrrRrBrDrVrQrWrar@r@r@rAsv  0