sg&dZddlmZmZmZddlZddlmZddl m Z ddl m Z m Z mZejeZGdd eZy) z$Feature extractor class for EnCodec.)ListOptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingc6eZdZdZddgZ ddededededef fd Zed e efd Z ed e efd Z dd e e jeeee jeeefde e eeefde ede ede e eefde ed efdZxZS)EncodecFeatureExtractora Constructs an EnCodec feature extractor. This feature extractor inherits from [`~feature_extraction_sequence_utils.SequenceFeatureExtractor`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Instantiating a feature extractor with the defaults will yield a similar configuration to that of the [facebook/encodec_24khz](https://huggingface.co/facebook/encodec_24khz) architecture. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. Use 1 for mono, 2 for stereo. sampling_rate (`int`, *optional*, defaults to 24000): The sampling rate at which the audio waveform should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value that is used to fill the padding values. chunk_length_s (`float`, *optional*): If defined the audio is pre-processed into chunks of lengths `chunk_length_s` and then encoded. overlap (`float`, *optional*): Defines the overlap between each chunk. It is used to compute the `chunk_stride` using the following formulae : `int((1.0 - self.overlap) * self.chunk_length)`. input_values padding_mask feature_size sampling_rate padding_valuechunk_length_soverlapc Ht|d|||d|||_||_y)N)rrr)super__init__rr)selfrrrrrkwargs __class__s i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/encodec/feature_extraction_encodec.pyrz EncodecFeatureExtractor.__init__7s/ wl-_lwpvw, returnc`|jyt|j|jzS)N)rintrrs r chunk_lengthz$EncodecFeatureExtractor.chunk_lengthEs-    &t**T-?-??@ @rc|j |jytdtd|jz |jzS)Ng?)rrmaxr r"r!s r chunk_stridez$EncodecFeatureExtractor.chunk_strideMs@    &$,,*>q#sT\\1T5F5FFGH Hr raw_audiopadding truncation max_lengthreturn_tensorsc |;||jk7rAtd|d|jd|jd|d tjd|r |r td|d }t t |t tfxr(t |d tjtt f}|r=|Dcgc]1}tj|tj j3}}n|s@t |tjs&tj|tj }nht |tjrN|jtjtjur|jtj}|s tj|jg}t!|D]\} } | j"d kDrtd | j$|j&dk(r+| j"dk7rtd| j$dd|j&d k(sw| j$dd k7std| j$ddd} t)d|i} |j*|j,||r]t/d|D}t1tj2||j*z } | dz |j*z|j,z}nc|r_t5d|D}t1tj6||j*z } | dz |j*z|j,z}d}n| } | ,|j9| ||||} |r| j;d| d<g} | j;dD]1} |j&dk(r| d} | j=| j3| | d<|| j?|} | Scc}w)a Main method to featurize and prepare for the model one or several sequence(s). Args: raw_audio (`np.ndarray`, `List[float]`, `List[np.ndarray]`, `List[List[float]]`): The sequence or batch of sequences to be processed. Each sequence can be a numpy array, a list of float values, a list of numpy arrays or a list of list of float values. The numpy array must be of shape `(num_samples,)` for mono audio (`feature_size = 1`), or `(2, num_samples)` for stereo audio (`feature_size = 2`). padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). truncation (`bool`, *optional*, defaults to `False`): Activates truncation to cut input sequences longer than `max_length` to `max_length`. max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors instead of list of python integers. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return Numpy `np.ndarray` objects. sampling_rate (`int`, *optional*): The sampling rate at which the `audio` input was sampled. It is strongly recommended to pass `sampling_rate` at the forward call to prevent silent errors. Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zB. Please make sure that the provided audio input was sampled with z and not .zIt is strongly recommended to pass the `sampling_rate` argument to this function. Failing to do so can result in silent errors that might be hard to debug.zABoth padding and truncation were set. Make sure you only set one.Tr)dtypez6Expected input shape (channels, length) but got shape r$z$Expected mono audio but example has z channelsz&Expected stereo audio but example has rc3:K|]}|jdywrNshape.0arrays r z3EncodecFeatureExtractor.__call__.. GEQ Gc3:K|]}|jdywr2r3r5s rr8z3EncodecFeatureExtractor.__call__..r9r:r*)r*r)r(return_attention_maskattention_maskr).N) r ValueErrorloggerwarningbool isinstancelisttuplenpndarrayasarrayfloat32Tr.float64astype enumeratendimr4rrr&r"minr floorr%ceilpadpopappendconvert_to_tensors)rr'r(r)r*r+r is_batchedaudioidxexample padded_inputsrnb_steps r__call__z EncodecFeatureExtractor.__call__TsT  $ 2 22 I$P**+,**+9]O1F NN\  z`a a _G y4- 0 jj1PRPZPZ\acgOh6i  LUV5E<>>VIVJy"**$E 9BJJ?I  2:: .9??bhhrzzFZ3Z!((4II.001I&i0 hLC||a #YZaZgZgYh!ijj  A%',,!*; #G VXHYGZZc!dee  A%'--*;q*@ #I'--XZJ[I\\e!fgg  h #^Y$?@    (T->->-JzOa GY GG bhhzD4E4E'EFG%kT->->>ARARR  GY GG bggj43D3D&DEF%kT->->>ARARR & ,    HH%%&- %M0=0A0ABR0S n- $((8 +G  A%!),    * + )5 n%  %)<<^LMqWs56O&)r$i]gNN)NFNNN)__name__ __module__ __qualname____doc__model_input_namesr floatrpropertyrr"r&rrErFrrAstrr r rr[ __classcell__)rs@rr r sV.(8"" $        AhsmAAIhsmII@D%*$(;?'+zT%[$rzz2BDeDUUVz%c? :;<zTN z SM z !sJ!78 z }z zrr )r_typingrrrnumpyrE!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsr r r get_loggerr\r?r rrrrksB+((I499   H %q6qr