o  h(@sddlZddlmZddlZddlZddlmZmZm Z m Z ddl m Z m Z er/ddlmZe eZded ed ejfd d Zee d dGddde ZdS)N)Union)add_end_docstringsis_torch_availableis_torchaudio_availablelogging)Pipelinebuild_pipeline_init_args),MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMESbpayload sampling_ratereturnc Cs|}d}d}dddd|d|d|d d d d g }z tj|tjtjd }Wn ty-tdw||}|d}t|tj} | j ddkrItd| S)z? 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 filenamerzMalformed soundfile) subprocessPopenPIPEFileNotFoundError ValueError communicatenp frombufferfloat32shape) r r aracformat_for_conversionffmpeg_commandffmpeg_process output_stream out_bytesaudior'/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/transformers/pipelines/audio_classification.py ffmpeg_reads8  r)T)has_feature_extractorcsbeZdZdZfddZdeejee fffdd Z ddd Z d d Z d d Z dddZZS)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). csjd|vr|ddurd|d<nd|vrd|d<tj|i||jdkr.td|jd|tdS)Ntop_kptzThe z is only available in PyTorch.)super__init__ frameworkr __class__check_model_typer )selfargskwargsr2r'r(r0]s  z$AudioClassificationPipeline.__init__inputsc stj|fi|S)a Classify the sequence(s) given as inputs. See the [`AutomaticSpeechRecognitionPipeline`] documentation for more information. Args: inputs (`np.ndarray` or `bytes` or `str` or `dict`): The inputs is either : - `str` that is the filename of the audio file, the file will be read at the correct sampling rate to get the waveform using *ffmpeg*. This requires *ffmpeg* to be installed on the system. - `bytes` it is supposed to be the content of an audio file and is interpreted by *ffmpeg* in the same way. - (`np.ndarray` of shape (n, ) of type `np.float32` or `np.float64`) Raw audio at the correct sampling rate (no further check will be done) - `dict` form can be used to pass raw audio sampled at arbitrary `sampling_rate` and let this pipeline do the resampling. The dict must be either be in the format `{"sampling_rate": int, "raw": np.array}`, or `{"sampling_rate": int, "array": np.array}`, where the key `"raw"` or `"array"` is used to denote the raw audio waveform. top_k (`int`, *optional*, defaults to None): The number of top labels that will be returned by the pipeline. If the provided number is `None` or higher than the number of labels available in the model configuration, it will default to the number of labels. function_to_apply(`str`, *optional*, defaults to "softmax"): The function to apply to the model output. By default, the pipeline will apply the softmax function to the output of the model. Valid options: ["softmax", "sigmoid", "none"]. Note that passing Python's built-in `None` will default to "softmax", so you need to pass the string "none" to disable any post-processing. Return: A list of `dict` with the following keys: - **label** (`str`) -- The label predicted. - **score** (`float`) -- The corresponding probability. )r/__call__)r4r8r6r7r'r(r9js&z$AudioClassificationPipeline.__call__NcKsxi}|dur|jjj|d<n||jjjkr|jjj}||d<|dur3|dvr.td|d||d<nd|d<ii|fS)Nr,)softmaxsigmoidnonez'Invalid value for `function_to_apply`: z2. Valid options are ['softmax', 'sigmoid', 'none']function_to_applyr:)modelconfig num_labelsr)r4r,r=r6postprocess_paramsr'r'r(_sanitize_parameterss    z0AudioClassificationPipeline._sanitize_parameterscCst|tr/|ds|drt|j}nt|d }|}Wdn1s*wYt|tr;t ||j j }t|t r| }d|vrPd|vsTd|vsTtd|dd}|durj|dd|dd}|d}|}||j j krd dl}trd d lm}ntd |||||j j }t|tjstd t|jd krtd|j ||j j dd}|jdur|j|jd}|S)Nzhttp://zhttps://rbr rawarrayzWhen passing a dictionary to AudioClassificationPipeline, the dict needs to contain a "raw" key containing the numpy array representing the audio and a "sampling_rate" key, containing the sampling_rate associated with that arraypathr) functionalztorchaudio is required to resample audio samples in AudioClassificationPipeline. The torchaudio package can be installed through: `pip install torchaudio`.z"We expect a numpy ndarray as inputrzFWe expect a single channel audio input for AudioClassificationPipeliner.)r return_tensors)dtype) isinstancestr startswithrequestsgetcontentopenreadbytesr)feature_extractorr dictcopyrpoptorchr torchaudiorG ImportErrorresample from_numpynumpyrndarray TypeErrorlenr torch_dtypeto)r4r8f_inputsin_sampling_raterWF processedr'r'r( preprocesssT             z&AudioClassificationPipeline.preprocesscCs|jdi|}|S)Nr')r>)r4 model_inputs model_outputsr'r'r(_forwardsz$AudioClassificationPipeline._forwardr-r:csv|dkr |jdd}n|dkr|jd}n|jd}||\}}|}|}fddt||D}|S)Nr:rr;cs$g|]\}}|jjj|dqS))scorelabel)r>r?id2label).0rl_idr4r'r( s$z;AudioClassificationPipeline.postprocess..)logitsr:r;topktolistzip)r4rir,r=probsscoresidslabelsr'rqr( postprocesss z'AudioClassificationPipeline.postprocess)NN)r-r:)__name__ __module__ __qualname____doc__r0rrr]rRrKr9rBrgrjr{ __classcell__r'r'r7r(r+Bs   (:r+)rtypingrr\rrMutilsrrrrbaser r models.auto.modeling_autor get_loggerr|loggerrRintrEr)r+r'r'r'r(s    $