`i&dZddlmZmZddlZddlmZddlm Z ddl m Z m Z m Z e jeZGdd eZd gZdS) z$Feature extractor class for EnCodec.)OptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingceZdZdZddgZ dded ed ed eed eef fd Ze deefdZ e deefdZ dde e jeeee jeeefdee eeefdeedeedee eefd eedefdZxZS)EncodecFeatureExtractora Constructs an EnCodec feature extractor. This feature extractor inherits from [`~feature_extraction_sequence_utils.SequenceFeatureExtractor`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Instantiating a feature extractor with the defaults will yield a similar configuration to that of the [facebook/encodec_24khz](https://huggingface.co/facebook/encodec_24khz) architecture. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. Use 1 for mono, 2 for stereo. sampling_rate (`int`, *optional*, defaults to 24000): The sampling rate at which the audio waveform should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value that is used to fill the padding values. chunk_length_s (`float`, *optional*): If defined the audio is pre-processed into chunks of lengths `chunk_length_s` and then encoded. overlap (`float`, *optional*): Defines the overlap between each chunk. It is used to compute the `chunk_stride` using the following formulae : `int((1.0 - self.overlap) * self.chunk_length)`. input_values padding_mask]N feature_size sampling_rate padding_valuechunk_length_soverlapc ^tjd|||d|||_||_dS)N)rrr)super__init__rr)selfrrrrrkwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/encodec/feature_extraction_encodec.pyrz EncodecFeatureExtractor.__init__7s@ wl-_lwwpvwww, returncL|jdSt|j|jzS)N)rintrrs r chunk_lengthz$EncodecFeatureExtractor.chunk_lengthEs)   &4t*T-??@@ @rc||j|jdStdtd|jz |jzS)Nrg?)rrmaxr"r$r#s r chunk_stridez$EncodecFeatureExtractor.chunk_strideMs>   &$,*>4q#sT\1T5FFGGHH HrF raw_audiopadding truncation max_lengthreturn_tensorsc V|2||jkr&td|d|jd|jd|d n(td|jjd|r|rtd |d }t t|ttfo,t|d tj ttf}|r d |D}n|s;t|tj s!tj |tj }n^t|tj rD|jtjtjur|tj }|stj |jg}t%|D]\}} | jdkrtd| j|jdkr)| jdkrtd| jdd|jdkr/| jddkrtd| jddd} t-d|i} |j|j||rXt3d|D}t5tj||jz } | dz |jz|jz}n^|rZt9d|D}t5tj||jz } | dz |jz|jz}d}n| } | 4|| ||||} |r| d| d<g} | dD]/} |jdkr| d} | | j0| | d<|| !|} | S)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 .zDIt is strongly recommended to pass the `sampling_rate` argument to `zN()`. 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.TrcXg|]'}tj|tjj(S)dtype)npasarrayfloat32T).0audios r z4EncodecFeatureExtractor.__call__..s,VVV5E<<<>VVVrr0z6Expected input shape (channels, length) but got shape rz$Expected mono audio but example has z channelsz&Expected stereo audio but example has r c30K|]}|jdVdSrNshaper6arrays r z3EncodecFeatureExtractor.__call__..( G GEQ G G G G G Grc30K|]}|jdVdSr<r=r?s rrAz3EncodecFeatureExtractor.__call__..rBrr+)r+r*r)return_attention_maskattention_maskr).N)"r ValueErrorloggerwarningr__name__bool isinstancelisttupler2ndarrayr3r4r1float64astyper5 enumeratendimr>rrr'r$minr"floorr&ceilpadpopappendconvert_to_tensors) rr(r)r*r+r,r is_batchedidxexample padded_inputsr nb_steps r__call__z EncodecFeatureExtractor.__call__TsYT  $ 222 F$FF*FF*FF5BFFF3 NN\W[WeWn\\\     z `aa a _G y4- 0 0 jj1PRPZ\acgOh6i6i    5VVIVVVII 5Jy"*$E$E 5 9BJ???II  2: . . 59?bhrzFZFZ3Z3Z!((44I 2I..01I&i00 h hLC|a !iZaZg!i!ijjj A%%',!*;*; !d VXHY!d!d!deee A%%'-*;q*@*@ !f'-XZJ[!f!f!fggg #^Y$?@@   (T->-JzOa - G GY G G GGG bhzD4E'EFFGG%kT->>ARR  - G GY G G GGG bgj43D&DEEFF%kT->>ARR & ,    HH%%&- %M T0=0A0ABR0S0S n- $((88 + +G A%%!),    * * * *(4 n%  %)<<^LLMr)rrrNN)NFNNN)rI __module__ __qualname____doc__model_input_namesr"floatrrpropertyr$r'rr2rNrLrJstrrr rr_ __classcell__)rs@rr r s.(8""*.#'      !  %      AhsmAAAXAIhsmIIIXI@D%*$(;?'+zzT%[$rz2BDeDUUVz%c? :;<zTN z SM z !sJ!78 z }z zzzzzzzzrr )rbtypingrrnumpyr2!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrr r get_loggerrIrGr __all__rrrros+*""""""""IIIIII4444449999999999  H % %qqqqq6qqqh % %r