:jP$ddlZddlZddlZddlZddlZddlZddlZddlm Z ddl m Z m Z m Z mZddlZddlmZddlmZmZej(j+dZGddeZGd d eZGd d ej4ZGd dZy)N)Path)CallableMappingOptionalUnion)Response)ConnectionError HTTPErrorzpyannoteai-sdkceZdZdZy)PyannoteAIFailedJobz2Raised when a job failed on the pyannoteAI web APIN__name__ __module__ __qualname____doc__j/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/pyannoteai/sdk/client.pyr r (s<rr ceZdZdZy)PyannoteAICanceledJobz8Raised when a job was canceled on the pyannoteAI web APINr rrrrr.sBrrcBeZdZdZdededeffd Zddeffd ZxZ S) _UploadingCallbackBytesIOaKBytesIO subclass that calls a callback during the upload process Parameters ---------- callback : Callable Callback called during upload as `callback(total_in_bytes, completed_in_bytes)` total_size : int Total size to upload (in bytes) initial_bytes : bytes Initial bytes to upload callback total_size initial_bytescN||_d|_||_t||y)Nr)r_completed_size _callbacksuper__init__)selfrrr __class__s rr z"_UploadingCallbackBytesIO.__init__As( % ! 'rreturnct||}|xjt|z c_|jr'|j |j |j|S)N)total completed)rreadrlenrr)r!sizedatar"s rr'z_UploadingCallbackBytesIO.readLsUw|D! D ) >> NNoo..   r)) rrrrrintbytesr r' __classcell__)r"s@rrr4s:  ( ( ( (urrceZdZdZdZd)deefdZdefdZ ded efd Z d)ded ee d efd Z e d Zejded dfdZded efdZdeeefd efdZ d*deeze eeezfzdeedeed efdZ d+dededzdedzdedzdededededede dzd efd Z d,deded efd!Z d-ded"e eefd#ed$ededzdedzdedzdedededed efd%Zd.d&ed'ed e fd(Zy)/ClientaOfficial client for pyannoteAI web API Parameters ---------- token : str, optional pyannoteAI API key created from https://dashboard.pyannote.ai. Defaults to using `PYANNOTEAI_API_KEY` environment variable. Usage ----- # instantiate client for pyannoteAI web API >>> from pyannoteai.sdk import Client >>> client = Client(token="{PYANNOTEAI_API_KEY}") # upload your audio file to the pyannoteAI web API # and store it for a few hours for later re-use. >>> media_url = client.upload("/path/to/your/audio.wav") # initiate a diarization job on the pyannoteAI web API >>> job_id = client.diarize(media_url) # retrieve prediction from pyannoteAI web API >>> prediction = client.retrieve(job_id) zhttps://api.pyannote.ai/v1Ntokenc d||_|xs tjjdd|_y)NPYANNOTEAI_API_KEY)r1osenvirongetapi_key)r!r1kwargss rr zClient.__init__ts% H /CR H rresponsecX|jdk(r td|jy)z9Raise an exception if the response status code is not 2xxiz Failed to authenticate to pyannoteAI API. Please create an API key on https://dashboard.pyannote.ai/ and provide it either via `PYANNOTEAI_API_KEY` environment variable or with `token` parameter.N) status_coder raise_for_status)r!r:s r_raise_for_statuszClient._raise_for_statusxs3   3 &^  !!#rrouter#c tj|j||j}|j ||S#t$r t dwxYw)a,Send GET authenticated request to pyannoteAI API Parameters ---------- route : str API route to send the GET request to. Returns ------- response : Response Raises ------ ConnectionError HTTPError )headers Failed to connect to pyannoteAI web API. Please check your internet connection or visit https://pyannote.openstatus.dev/ to check the status of the pyannoteAI web API.)requestsr7API_URL_headersr r>)r!r?r:s r_authenticated_getzClient._authenticated_getsa$ ||t||nUG$)r!r?rGr:s r_authenticated_postzClient._authenticated_postsf( }}<<.(tT]]H x( !\  s 0AAc|jSN)_api_key)r!s rr8zClient.api_keys }}rr8c|s td||_d|jdtdd|_|j dy)Nz Failed to authenticate to pyannoteAI web API. Please create an API key on https://dashboard.pyannote.ai/ and provide it either via `PYANNOTEAI_API_KEY` environment variable or with `token` parameter.zBearer zpyannoteAI-sdk-python/zapplication/json) Authorizationz User-Agentz Content-Typez/test) ValueErrorrM __version__rErF)r!r8s rr8zClient.api_keysU^   &t}}o62;-@.  (r media_urlcR|jdd|i}|jdS)aZCreate a presigned URL to upload audio file to pyannoteAI platform Parameters ---------- media_url : str Unique identifier used to retrieve the uploaded audio file on the pyannoteAI platform. Any combination of letters (a-z, A-Z), digits (0-9), and the characters -./ prefixed with media:// is allowed. One would usually use a string akin to a path on filesystem (e.g. "media://path/to/audio.wav"). Returns ------- url : str Presigned URL to upload audio file to pyannoteAI platform z /media/inputurlrG)rJrG)r!rRr:s r_create_presigned_urlzClient._create_presigned_urls/"++N%AS+T}}u%%rfilectj}t|d5tfddD]}|j | ddd|j S#1swY|j SxYw)zACompute MD5 hash of a file (used for media_url when not provided)rbc&jdS)Ni)r')fsrz"Client._hash_md5..saffTlrrN)hashlibmd5openiterupdate hexdigest)r!rWhash_md5chunkr[s @r _hash_md5zClient._hash_md5sq;;= $  '2C8 '& ' '!!## '!!##s &A!!A9audiorcd}t|trd|vr|d}nd|vrd} ddl}|d}|d}t |dd r|dj d }t jd d 5}|jjj|j||j|j|j}dddn td tj j#|} |d|j%|}t'|d5}t)|| |j+} dddt|t,r|j/dstd|d|j1|} t3j4|  } |r5tj j9|rtj:| | j=t?j@d|S#t$r tdwxYw#1swY?xYw#1swYxYw#t6$rt7d| dwxYw#|r6tj j9|rtj:|wwwxYw)aUpload audio file to pyannoteAI platform Parameters ---------- audio : str or Path or dict Path to audio file to be uploaded. Can be a "str" or "Path" instance, or a dict with an "audio" key (e.g. {"audio": "/path/to/audio.wav"}). media_url : str, optional Unique identifier used to retrieve the uploaded audio file on the pyannoteAI platform. Any combination of letters {a-z, A-Z}, digits {0-9}, and {-./} characters prefixed with 'media://' is allowed. One would usually use a string akin to a path on filesystem (e.g. "media://path/to/audio.wav"). Defaults to media://{md5-hash-of-audio-file}. callback : Callable, optional When provided, `callback` is called during the uploading process with the following signature: callback(total=..., # number of bytes to upload completed=...) # number of bytes uploaded) Returns ------- media_url : str Same as the input `media_url` parameter when provided, or "media://{md5-hash-of-audio-file}" otherwise. FrfwaveformTrNz>To process the waveform directly, you need to install `scipy`. sample_ratenumpy)forcez.wav)suffixdeletezRWhen `audio` is a dict, it must provide the path to the audio file in 'audio' key.zmedia://rYz Invalid media URI: zp. Any combination of letters {a-z, A-Z}, digits {0-9}, and {-./} characters prefixed with 'media://' is allowed.)r*z) Failed to upload audio to presigned URL z|. Please check your internet connection or visit https://pyannote.openstatus.dev/ to check the status of the pyannoteAI API.aR You are using pyannoteAI's temporary storage solution. Your file will be permanently deleted from our servers within 24hs. If you are running in production, we highly recommend to use your own storage to reduce network latency and obtain results faster. Please check our documentation at https://docs.pyannote.ai/ for more information.)! isinstancerscipy.io ImportErrorhasattrrjtempfileNamedTemporaryFileiowavfilewritenamesqueezeflushrPr5pathgetsizerer_rr'str startswithrVrCputr existsremover=warningswarn) r!rfrRrrmscipyrirhr[rr* presigned_urlr:s ruploadz Client.uploads@ eW %%gu$# $M2  ,5,g6$Z066T6BH00uM#QRHH$$**166;@P@P@RSGGIFFE## !h WW__U+  "4>>%#8"9:I%  M!-Xz1668LD M 9c*y/C/CJ/O;<? 229=  !||M=H"''../ %  !!# U V E#%X##" M M$ !))68{~  "''../ % 0vs<G:-AHHH+:HHH(+II:J num_speakers min_speakers max_speakers confidenceturn_level_confidence exclusivemodel transcriptiontranscription_configc ||||||||| d } | | | d<| j| |jd| } | j}|dS)a,Initiate a diarization job on the pyannoteAI web API Parameters ---------- media_url : str media://{...} URL created with the `upload` method or any other public URL pointing to an audio file. num_speakers : int, optional Force number of speakers to diarize. If not provided, the number of speakers will be determined automatically. min_speakers : int, optional Minimum number of speakers. max_speakers : int, optional Maximum number of speakers. confidence : bool, optional Enable confidence scores. turn_level_confidence: bool, optional Enable turn-based confidence scores. exclusive: bool, optional Enable exclusive speaker diarization. model : str, optional Defaults to "precision-2" transcription : bool, optional Enable STT orchestration. transcription_config : dict, optional STT configuration parameters, including model selection. **kwargs : optional Extra arguments to send in the body of the request. Returns ------- job_id: str Raises ------ HTTPError If something else went wrong ) rTr numSpeakers minSpeakers maxSpeakersrturnLevelConfidencerrtranscriptionConfigz/diarizerUjobIdrarJrG)r!rRrrrrrrrrrr9rGr:r*s rdiarizezClient.diarizeksrl'''$#8"*   +*>D& ' F++JT+B}}G}rc ~||d}|j||jd|}|j}|dS)a)Initiate a voiceprint job on the pyannoteAI web API Parameters ---------- media_url : str media://{...} URL created with the `upload` method or any other public URL pointing to an audio file. model : str, optional Defaults to "precision-2". **kwargs : optional Extra arguments to send in the body of the request. Returns ------- job_id: str Raises ------ HTTPError If something else went wrong )rTrz /voiceprintrUrr)r!rRrr9rGr:r*s r voiceprintzClient.voiceprintsD8!51 F++M+E}}G}r voiceprintsexclusive_matchingmatching_thresholdc  || ||||| | |jD cgc] \} }| |d c}} ||dd }|j| |jd|}|j}|dScc}} w)aInitiate an identification job on the pyannoteAI web API Parameters ---------- media_url : str media://{...} URL created with the `upload` method or any other public URL pointing to an audio file. voiceprints : dict Voiceprints. exclusive_matching : bool, optional Prevent multiple speakers from being matched to the same voiceprint. Defaults to True. matching_threshold : float, optional Prevent matching if confidence score is below this threshold. Value is between 0 and 100. Default is 0, meaning all voiceprints are matched. num_speakers : int, optional Force number of speakers to diarize. If not provided, the number of speakers will be determined automatically. min_speakers : int, optional Minimum number of speakers. max_speakers : int, optional Maximum number of speakers. confidence : bool, optional Enable confidence scores. turn_level_confidence: bool, optional Enable turn-based confidence scores. exclusive: bool, optional Enable exclusive speaker diarization. model : str, optional Defaults to "precision-2" **kwargs : optional Extra arguments to send in the body of the request. Returns ------- job_id: str Raises ------ HTTPError If something else went wrong )labelr)r threshold) rTrrrrrrrrmatchingz /identifyrUr)itemsrarJrG)r!rRrrrrrrrrrrr9speakerrrGr:r*s ridentifyzClient.identifysv'''$#8",7+<+<+>'GZ"< 0/ & F++Kd+C}}G}sA.job_id every_secondscd} |jd|j}|d}|dvrtj|B |dk(r6|j dt j dd}t |||d k(r6|j dt j dd}t||tjd |S) aRetrieve output of a job (once completed) from pyannoteAI web API Parameters ---------- job_id : str Job ID. Returns ------- job_output : dict Job output Raises ------ PyannoteAIFailedJob If the job failed PyannoteAICanceledJob If the job was canceled HTTPError If something else went wrong Nz/jobs/status) succeededcanceledfailedroutputerrorzPlease contact support.ra You are using periodic polling to retrieve results. If you are running in production, we highly recommend to setup a webhook server to obtain results faster, as soon as they are available. Please check our documentation at https://docs.pyannote.ai/ for more information.) rFrGtimesleepr7dictr rrr)r!rr job_statusjobrs rretrievezClient.retrieve-s. ))F6(*;<AACCXJ!DD =)   !GGHdf-11';TUE%eV4 4  #GGHdf-11';TUE'v6 6 U V  rrL)NN) NNNFFF precision-2FN)r) TgNNNFFFr) )rrrrrDrr|r rr>rFrrJpropertyr8setterrVrrrerrr,boolrrfloatrrrrrr0r0Ws4+GIhsmI $( $>!!HTN!h!F ^^)s)t))$&s&s&($eCI.$3$$('+ lTzDcDj11lC=l8$ l lb$(#'#' &+"#,0IIDjIDj I Dj I  I $IIII#TkI I\#""" "P$($'#'#'#' &+"QQ#s(^Q! Q " Q Dj QDjQDjQQ $QQQ Qf0s0300rr0)r]importlib.metadata importlibrtr5rrrrpathlibrtypingrrrrrCrrequests.exceptionsr r metadataversionrQ Exceptionr rBytesIOrr0rrrrsz.  55:  (()9:  )  I  FFFr