o i'@s"ddlmZddlZddlmZmZmZmZddlm Z m Z ddl m Z ddl mZmZddlmZddlmZdd lmZmZGd d d eZGd d d eZGdddeZedZeeefZdZGdddZddddd2ddZGd d!d!Z d3d&d'Z!   ( (d4ed)d5d0d1Z"dS)6) annotationsN)DictLiteralOptional TypedDict) HTTPErrorURLError) urlencode)Requesturlopen) NotRequired) AudioData) RequestErrorUnknownValueErrorc@eZdZUded<ded<dS) Alternativestr transcriptfloat confidenceN__name__ __module__ __qualname____annotations__rrX/home/kuhnn/.local/lib/python3.10/site-packages/speech_recognition/recognizers/google.pyr  rc@r)Resultlist[Alternative] alternativeboolfinalNrrrrrrrrc@r)GoogleResponsez list[Result]resultzNotRequired[int] result_indexNrrrrrr#rr#)rz-http://www.google.com/speech-api/v2/recognizec@sLeZdZdd d ZdddZd ddZd!ddZd"ddZed#ddZ dS)$RequestBuilderendpointrkeylanguage filter_levelProfanityFilterLevelreturnNonecCs||_||_||_||_dSNr(r)r*r+)selfr(r)r*r+rrr__init__%s zRequestBuilder.__init__ audio_datar r cCs@t|ts td|}||}||}t|||d}|S)Nz!``audio_data`` must be audio data)dataheaders) isinstancer ValueError build_url build_headers build_datar )r1r3urlr5 flac_datarequestrrrbuild2s   zRequestBuilder.buildcCs(td|j|j|jd}|jd|S)a* >>> builder = RequestBuilder(endpoint="http://www.google.com/speech-api/v2/recognize", key="awesome-key", language="en-US", filter_level=0) >>> builder.build_url() 'http://www.google.com/speech-api/v2/recognize?client=chromium&lang=en-US&key=awesome-key&pFilter=0' chromium)clientlangr)pFilter?)r r*r)r+r()r1paramsrrrr8<szRequestBuilder.build_urlRequestHeaderscCs|j}dd|i}|S)z >>> builder = RequestBuilder(endpoint="", key="", language="", filter_level=1) >>> audio_data = AudioData(b"", 16_000, 1) >>> builder.build_headers(audio_data) {'Content-Type': 'audio/x-flac; rate=16000'} z Content-Typezaudio/x-flac; rate= sample_rate)r1r3rater5rrrr9LszRequestBuilder.build_headersbytescCs|j||jdd}|S)N) convert_rate convert_width) get_flac_datato_convert_raterG)r1r3r<rrrr:Ws  zRequestBuilder.build_datarGint Optional[int]cCs|dkrdSdS)zAudio samples must be at least 8 kHz >>> RequestBuilder.to_convert_rate(16_000) >>> RequestBuilder.to_convert_rate(8_000) >>> RequestBuilder.to_convert_rate(7_999) 8000 i@NrrFrrrrN^s zRequestBuilder.to_convert_rateN) r(rr)rr*rr+r,r-r.)r3r r-r )r-r)r3r r-rE)r3r r-rI)rGrOr-rP) rrrr2r>r8r9r: staticmethodrNrrrrr'$s   r'en-US)r)r*r+r(rr) str | Noner*r+r,r-cCsHt|ts td|durt|tstd|durd}t||||dS)Nz``language`` must be a stringz$``key`` must be ``None`` or a stringz'AIzaSyBOti4mM-6x9WDnZIjIeyEU21OpBXqWBgwr0)r6rr7r'r0rrrcreate_request_builderjs rTc@s<eZdZdddZdd d Zedd dZedddZdS) OutputParsershow_allr!with_confidencer-r.cCs||_||_dSr/rVrW)r1rVrWrrrr2s zOutputParser.__init__ response_textrcCsH||}|jr |S||d}|dd}|jr |d|fS|dS)Nr rg?r)convert_to_resultrVfind_best_hypothesisgetrW)r1rY actual_resultbest_hypothesisrrrrparses   zOutputParser.parsercCs`|dD]'}|s qt|d}t|dkr,t|ddgdkr&t|dSqt)a >>> response_text = '''{"result":[]} ... {"result":[{"alternative":[{"transcript":"one two three","confidence":0.49585345},{"transcript":"1 2","confidence":0.42899391}],"final":true}],"result_index":0} ... ''' >>> OutputParser.convert_to_result(response_text) {'alternative': [{'transcript': 'one two three', 'confidence': 0.49585345}, {'transcript': '1 2', 'confidence': 0.42899391}], 'final': True} >>> OutputParser.convert_to_result("") Traceback (most recent call last): ... speech_recognition.exceptions.UnknownValueError >>> OutputParser.convert_to_result('\n{"result":[]}') Traceback (most recent call last): ... speech_recognition.exceptions.UnknownValueError >>> OutputParser.convert_to_result('{"result":[{"foo": "bar"}]}') Traceback (most recent call last): ... speech_recognition.exceptions.UnknownValueError >>> OutputParser.convert_to_result('{"result":[{"alternative": []}]}') Traceback (most recent call last): ... speech_recognition.exceptions.UnknownValueError  r$rr )splitjsonloadslenr\r)rYliner$rrrrZs  zOutputParser.convert_to_result alternativesrrcCs4d|vr t|ddd}n|d}d|vrt|S)a >>> alternatives = [{"transcript": "one two three", "confidence": 0.42899391}, {"transcript": "1 2", "confidence": 0.49585345}] >>> OutputParser.find_best_hypothesis(alternatives) {'transcript': 'one two three', 'confidence': 0.42899391} >>> alternatives = [{"confidence": 0.49585345}] >>> OutputParser.find_best_hypothesis(alternatives) Traceback (most recent call last): ... speech_recognition.exceptions.UnknownValueError rcSs|dS)Nrr)r rrrsz3OutputParser.find_best_hypothesis..)r)rr)maxr)rfr^rrrr[sz!OutputParser.find_best_hypothesisN)rVr!rWr!r-r.)rYr)rYrr-r)rfrr-r)rrrr2r_rQrZr[rrrrrUs   $rUr=r timeoutrOc Csnzt||d}Wn'ty}ztd|jd}~wty/}ztd|jd}~ww|dS)Nrizrecognition request failed: {}z!recognition connection failed: {}zutf-8)r rrformatreasonrreaddecode)r=riresponseerrrobtain_transcriptions rqF)r(r3r pfilterrVr!rWc Cs>t||||d}||} t| |jd} t||d} | | S)aPerforms speech recognition on ``audio_data`` (an ``AudioData`` instance), using the Google Speech Recognition API. The Google Speech Recognition API key is specified by ``key``. If not specified, it uses a generic key that works out of the box. This should generally be used for personal or testing purposes only, as it **may be revoked by Google at any time**. To obtain your own API key, simply following the steps on the `API Keys `__ page at the Chromium Developers site. In the Google Developers Console, Google Speech Recognition is listed as "Speech API". The recognition language is determined by ``language``, an RFC5646 language tag like ``"en-US"`` (US English) or ``"fr-FR"`` (International French), defaulting to US English. A list of supported language tags can be found in this `StackOverflow answer `__. The profanity filter level can be adjusted with ``pfilter``: 0 - No filter, 1 - Only shows the first character and replaces the rest with asterisks. The default is level 0. Returns the most likely transcription if ``show_all`` is false (the default). Otherwise, returns the raw API response as a JSON dictionary. Raises a ``speech_recognition.UnknownValueError`` exception if the speech is unintelligible. Raises a ``speech_recognition.RequestError`` exception if the speech recognition operation failed, if the key isn't valid, or if there is no internet connection. r0rjrX)rTr>rqoperation_timeoutrUr_) recognizerr3r)r*rrrVrWr(request_builderr=rY output_parserrrrrecognize_legacys  rw) r(rr)rSr*rr+r,r-r')r=r rirOr-r)NrRrFF)r3r r)rSr*rrrr,rVr!rWr!r(r)# __future__rrbtypingrrrr urllib.errorrr urllib.parser urllib.requestr r typing_extensionsr speech_recognition.audior speech_recognition.exceptionsrrrrr#r,rrEENDPOINTr'rTrUrqrwrrrrs<     I V