+ QV-jS+^RIt^RIHt^RIt^RIt^RIHtHtH t H t H t ^RI H t Ht]!4'd^RIHt] P"!]4tRRlt]!]!RR 74!R R ] 44tR#) N)Any)add_end_docstringsis_torch_availableis_torchaudio_availableis_torchcodec_availablelogging)Pipelinebuild_pipeline_init_args),MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMEScPV^8dQhR\R\R\P/#)bpayload sampling_ratereturn)bytesintnpndarray)formats"|/Volumes/fast/ai/experiments/ui-tars-smoke/.venv/lib/python3.14/site-packages/transformers/pipelines/audio_classification.py __annotate__rs%!!%!! !c T pRpRpRRRRVRVRVR R R R . p\P!V\P\PR 7pTP T4pT^,p\ P!T\ P4p T P^,^8Xd \ R4hT # \d \ R4hi;i)z7 Helper function to read an audio file through ffmpeg. 1f32leffmpegz-izpipe:0z-acz-arz-fz -hide_bannerz -loglevelquietzpipe:1)stdinstdoutzFffmpeg was not found but is required to load audio files from filenamezMalformed soundfile) subprocessPopenPIPEFileNotFoundError ValueError communicater frombufferfloat32shape) rraracformat_for_conversionffmpeg_commandffmpeg_process output_stream out_bytesaudios && r ffmpeg_readr1s ?B B#      N c#)). XbXgXgh#..x8Ma I MM)RZZ 0E {{1~.// L cabbcs 5B11CT)has_feature_extractorc~aa]tRt^BtoRtRtRtRtRtV3Rlt V3RlV3Rllt R Rlt Rt R t R R ltR tVtV;t#)AudioClassificationPipelinea Audio classification pipeline using any `AutoModelForAudioClassification`. This pipeline predicts the class of a raw waveform or an audio file. In case of an audio file, ffmpeg should be installed to support multiple audio formats. Example: ```python >>> from transformers import pipeline >>> classifier = pipeline(model="superb/wav2vec2-base-superb-ks") >>> classifier("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/1.flac") [{'score': 0.997, 'label': '_unknown_'}, {'score': 0.002, 'label': 'left'}, {'score': 0.0, 'label': 'yes'}, {'score': 0.0, 'label': 'down'}, {'score': 0.0, 'label': 'stop'}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"audio-classification"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=audio-classification). FTc<RV9dVR,fRVR&M RV9d^VR&\SV`!V/VBVP\4R#)top_kN)super__init__check_model_typer )selfargskwargs __class__s&*,rr8$AudioClassificationPipeline.__init__csO f !8"F7O F "F7O $)&) JKrc <V^8dQhRS[PS[,S[,S[,RS[RS[S[S[S[3,,/#)r inputsr<r)rrrstrdictrlist)r __classdict__s"rr(AudioClassificationPipeline.__annotate__msH"2"2rzzE1C7$>"2#"2RVW[\_ad\dWeRf"2rc &<\SV`!V3/VB#)a Classify the sequence(s) given as inputs. See the [`AutomaticSpeechRecognitionPipeline`] documentation for more information. Args: inputs (`np.ndarray` or `bytes` or `str` or `dict`): The inputs is either : - `str` that is the filename of the audio file, the file will be read at the correct sampling rate to get the waveform using *ffmpeg*. This requires *ffmpeg* to be installed on the system. - `bytes` it is supposed to be the content of an audio file and is interpreted by *ffmpeg* in the same way. - (`np.ndarray` of shape (n, ) of type `np.float32` or `np.float64`) Raw audio at the correct sampling rate (no further check will be done) - `dict` form can be used to pass raw audio sampled at arbitrary `sampling_rate` and let this pipeline do the resampling. The dict must be either be in the format `{"sampling_rate": int, "raw": np.array}`, or `{"sampling_rate": int, "array": np.array}`, where the key `"raw"` or `"array"` is used to denote the raw audio waveform. top_k (`int`, *optional*, defaults to None): The number of top labels that will be returned by the pipeline. If the provided number is `None` or higher than the number of labels available in the model configuration, it will default to the number of labels. function_to_apply (`str`, *optional*, defaults to "softmax"): The function to apply to the model output. By default, the pipeline will apply the softmax function to the output of the model. Valid options: ["softmax", "sigmoid", "none"]. Note that passing Python's built-in `None` will default to "softmax", so you need to pass the string "none" to disable any post-processing. Return: A list of `dict` with the following keys: - **label** (`str`) -- The label predicted. - **score** (`float`) -- The corresponding probability. )r7__call__)r:r@r<r=s&&,rrG$AudioClassificationPipeline.__call__msDw1&11rc 8/pVf%VPPPVR&MHWPPP8d!VPPPpWR&VeVR9d\RV R24hW$R&MRVR&//V3#)Nr6softmaxz'Invalid value for `function_to_apply`: z2. Valid options are ['softmax', 'sigmoid', 'none']function_to_apply)rJsigmoidnone)modelconfig num_labelsr$)r:r6rKr<postprocess_paramss&&&, r_sanitize_parameters0AudioClassificationPipeline._sanitize_parameterss =*.***;*;*F*F w 'zz((333 ))44*/w '  ( (FF =>O=PQGG7H2 36? 2 32)))rc\V\4'dVPR4'gVPR4'd$\P!VRR7P pM-\ VR4;_uu_4pVP4pRRR4\V\4'd \WPP4p\4'd>^RI p\WP4'dVP4P!4p\#4'dZ^RI p^RIp\WP&P(4'd-VP+4pVP,pRVRVP./p\V\04'Ed$VP34pRV9dRV9gRV9g \5R 4hVP7RR4pVf%VP7R R4VP7RR4pVP7R4pTpWPP8wd^RI p\94'd^R IHp M \?R 4hT PA\V\BPD4'dVPGV4MTVVPP4P!4p\V\BPD4'g \IR 4h\KVPL4^8wd \5R4hVPWPPRR7p VPNeV PQVPNR7p V # +'giEL;i)zhttp://zhttps://T)follow_redirectsrbNarrayrrawzWhen passing a dictionary to AudioClassificationPipeline, the dict needs to contain a "raw" key containing the numpy array or torch tensor representing the audio and a "sampling_rate" key, containing the sampling_rate associated with that arraypath) functionalztorchaudio is required to resample audio samples in AudioClassificationPipeline. The torchaudio package can be installed through: `pip install torchaudio`.z2We expect a numpy ndarray or torch tensor as inputzFWe expect a single channel audio input for AudioClassificationPipelinept)rreturn_tensors)dtype)) isinstancerA startswithhttpxgetcontentopenreadrr1feature_extractorrrtorchTensorcpunumpyr torchcodecdecoders AudioDecoderget_all_samplesdata sample_raterBcopyr$popr torchaudiorZ ImportErrorresamplerr from_numpy TypeErrorlenr(r]to) r:r@frfrj_audio_samples_array_inputsin_sampling_rateF processeds && r preprocess&AudioClassificationPipeline.preprocesss fc " "  ++v/@/@/L/L6DAII&$''1VVXF( fe $ $ )?)?)M)MNF    &,,//++- " $ $  &"5"5"B"BCC!'!7!7!9',,!6?Nrsj uu4X   H %!H,4HIA(AJAr