͑iwHD%SSKJr SSKJr SSKJrJr SSKJr SSK r SSK J r SSK J r J r Jr SS KJr \(aSS K Jr \S rS \S '"SS\ R(5r"SS\ R(5r"SS\ R(5r"SS\ R(5rg)) annotations)partial) TYPE_CHECKINGLiteral) TypeAliasN)nn)compute_fbank_matrix create_dct power_to_db) get_window)Tensor) hamminghannkaiserbartlettnuttallgaussian exponentialtriangbohmanblackmancosinetukeytaylorr_WindowLiteralc^\rSrSr%SrS\S'S\S'S S U4SjjjrS SjrS rU=r $) Spectrogram/aBCompute spectrogram of given signals, typically audio waveforms. The spectrogram is defined as the complex norm of the short-time Fourier transformation. Args: n_fft (int, optional): The number of frequency components of the discrete Fourier transform. Defaults to 512. hop_length (Optional[int], optional): The hop length of the short time FFT. If `None`, it is set to `win_length//4`. Defaults to None. win_length (Optional[int], optional): The window length of the short time FFT. If `None`, it is set to same as `n_fft`. Defaults to None. window (str, optional): The window function applied to the signal before the Fourier transform. Supported window functions: 'hamming', 'hann', 'gaussian', 'exponential', 'triang', 'bohman', 'blackman', 'cosine', 'tukey', 'taylor', 'bartlett', 'kaiser', 'nuttall'. Defaults to 'hann'. power (float, optional): Exponent for the magnitude spectrogram. Defaults to 2.0. center (bool, optional): Whether to pad `x` to make that the :math:`t imes hop\_length` at the center of `t`-th frame. Defaults to True. pad_mode (str, optional): Choose padding pattern when `center` is `True`. Defaults to 'reflect'. dtype (str, optional): Data type of input and window. Defaults to 'float32'. Returns: :ref:`api_paddle_nn_Layer`. An instance of Spectrogram. Examples: .. code-block:: python >>> import paddle >>> from paddle.audio.features import Spectrogram >>> sample_rate = 16000 >>> wav_duration = 0.5 >>> num_channels = 1 >>> num_frames = sample_rate * wav_duration >>> wav_data = paddle.linspace(-1.0, 1.0, int(num_frames)) * 0.1 >>> waveform = wav_data.tile([num_channels, 1]) >>> feature_extractor = Spectrogram(n_fft=512, window = 'hann', power = 1.0) >>> feats = feature_extractor(waveform) floatpowerr fft_windowc >[T U]5 US:dS5eXPlUcUn[XCSUS9Ul[ [ RRUUUURUUS9Ul URSUR5 g)Nrz!Power of spectrogram must be > 0.T)fftbinsdtype)n_fft hop_length win_lengthwindowcenterpad_moder") super__init__r!r r"rpaddlesignalstft_stftregister_buffer) selfr&r'r(r)r!r*r+r% __class__s \/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/audio/features/layers.pyr-Spectrogram.__init__Vs qy===y  J$ E  MM  !!??   \4??;cURU5n[R"[R"U5UR5nU$)z Args: x (Tensor): Tensor of waveforms with shape `(N, T)` Returns: Tensor: Spectrograms with shape `(N, n_fft//2 + 1, num_frames)`. )r1r.powabsr!)r3xr0 spectrograms r5forwardSpectrogram.forwardws4zz!}jjD!14::> r7)r1r"r!)r?Nr?Treflectfloat32)r&intr' int | Noner(rDr)rr!r r*boolr+Literal['reflect']r%strreturnNoner;rrHr __name__ __module__ __qualname____firstlineno____doc____annotations__r-r=__static_attributes__ __classcell__r4s@r5rr/s!F L!$!%!''0<<< <  <  <<%<< <>> import paddle >>> from paddle.audio.features import MelSpectrogram >>> sample_rate = 16000 >>> wav_duration = 0.5 >>> num_channels = 1 >>> num_frames = sample_rate * wav_duration >>> wav_data = paddle.linspace(-1.0, 1.0, int(num_frames)) * 0.1 >>> waveform = wav_data.tile([num_channels, 1]) >>> feature_extractor = MelSpectrogram(sr=sample_rate, n_fft=512, window = 'hann', power = 1.0) >>> feats = feature_extractor(waveform) rCn_melsr f_minf_maxrEhtkLiteral['slaney'] | floatnormr fbank_matrixc >[TU]5 [UUUUUUUUS9UlXlXlXlXlXlU cUS-n [UUU U U U U US9Ul URSUR5 g)N)r&r'r(r)r!r*r+r%r )srr&rXrYrZr[r]r%r^) r,r-r _spectrogramrXrYrZr[r]r r^r2)r3r`r&r'r(r)r!r*r+rXrYrZr[r]r%r4s r5r-MelSpectrogram.__init__s" '!!      =!GE0   ^T->->?r7cjURU5n[R"URU5nU$)z Args: x (Tensor): Tensor of waveforms with shape `(N, T)` Returns: Tensor: Mel spectrograms with shape `(N, n_mels, num_frames)`. )rar.matmulr^)r3r; spect_feature mel_features r5r=MelSpectrogram.forwards0))!, mmD$5$5}E r7)rarZrYr^r[rXr])"Vir?Nr@TrA@I@NFslaneyrB)r`rCr&rCr'rDr(rDr)rr!r r*rEr+rFrXrCrYr rZ float | Noner[rEr]r\r%rGrHrIrJrKrTs@r5rVrVs$L K L L I ##!$!%!''0"*2.@ .@.@ .@  .@  .@.@.@%.@.@.@.@.@(.@.@ !.@.@`  r7rVc^\rSrSr%SrS\S'S\S'S\S'S S U4SjjjrS S jrS rU=r $)LogMelSpectrograma Compute log-mel-spectrogram feature of given signals, typically audio waveforms. Args: sr (int, optional): Sample rate. Defaults to 22050. n_fft (int, optional): The number of frequency components of the discrete Fourier transform. Defaults to 512. hop_length (Optional[int], optional): The hop length of the short time FFT. If `None`, it is set to `win_length//4`. Defaults to None. win_length (Optional[int], optional): The window length of the short time FFT. If `None`, it is set to same as `n_fft`. Defaults to None. window (str, optional): The window function applied to the signal before the Fourier transform. Supported window functions: 'hamming', 'hann', 'gaussian', 'exponential', 'triang', 'bohman', 'blackman', 'cosine', 'tukey', 'taylor', 'bartlett', 'kaiser', 'nuttall'. Defaults to 'hann'. power (float, optional): Exponent for the magnitude spectrogram. Defaults to 2.0. center (bool, optional): Whether to pad `x` to make that the :math:`t imes hop\_length` at the center of `t`-th frame. Defaults to True. pad_mode (str, optional): Choose padding pattern when `center` is `True`. Defaults to 'reflect'. n_mels (int, optional): Number of mel bins. Defaults to 64. f_min (float, optional): Minimum frequency in Hz. Defaults to 50.0. f_max (Optional[float], optional): Maximum frequency in Hz. Defaults to None. htk (bool, optional): Use HTK formula in computing fbank matrix. Defaults to False. norm (Union[str, float], optional): Type of normalization in computing fbank matrix. Slaney-style is used by default. You can specify norm=1.0/2.0 to use customized p-norm normalization. Defaults to 'slaney'. ref_value (float, optional): The reference value. If smaller than 1.0, the db level of the signal will be pulled up accordingly. Otherwise, the db level is pushed down. Defaults to 1.0. amin (float, optional): The minimum value of input magnitude. Defaults to 1e-10. top_db (Optional[float], optional): The maximum db value of spectrogram. Defaults to None. dtype (str, optional): Data type of input and window. Defaults to 'float32'. Returns: :ref:`api_paddle_nn_Layer`. An instance of LogMelSpectrogram. Examples: .. code-block:: python >>> import paddle >>> from paddle.audio.features import LogMelSpectrogram >>> sample_rate = 16000 >>> wav_duration = 0.5 >>> num_channels = 1 >>> num_frames = sample_rate * wav_duration >>> wav_data = paddle.linspace(-1.0, 1.0, int(num_frames)) * 0.1 >>> waveform = wav_data.tile([num_channels, 1]) >>> feature_extractor = LogMelSpectrogram(sr=sample_rate, n_fft=512, window = 'hann', power = 1.0) >>> feats = feature_extractor(waveform) r ref_valueaminrmtop_dbc~>[TU]5 [UUUUUUUUU U U U U US9UlXlXlUUlg)N)r`r&r'r(r)r!r*r+rXrYrZr[r]r%)r,r-rV_melspectrogramrqrrrs)r3r`r&r'r(r)r!r*r+rXrYrZr[r]rqrrrsr%r4s r5r-LogMelSpectrogram.__init__sZ( -!! "#  r7c|URU5n[UURURURS9nU$)z Args: x (Tensor): Tensor of waveforms with shape `(N, T)` Returns: Tensor: Log mel spectrograms with shape `(N, n_mels, num_frames)`. )rqrrrs)rur rqrrrs)r3r;rflog_mel_features r5r=LogMelSpectrogram.forwardHs>**1- % nn;;   r7)rurrrqrs)rhr?NNrriTrArjrkNFrlr@绽|=NrB)$r`rCr&rCr'rDr(rDr)rr!r r*rEr+rFrXrCrYr rZrmr[rEr]r\rqr rrr rsrmr%rGrHrIrJrKrTs@r5roros'R K !%!%!''0"*2#%) )) )  )  )))%)))))()) !)"#)$%)& '))Vr7roc^\rSrSr%SrS\S'SS U4SjjjrS SjrSrU=r $) MFCCiZa Compute mel frequency cepstral coefficients(MFCCs) feature of given waveforms. Args: sr (int, optional): Sample rate. Defaults to 22050. n_mfcc (int, optional): [description]. Defaults to 40. n_fft (int, optional): The number of frequency components of the discrete Fourier transform. Defaults to 512. hop_length (Optional[int], optional): The hop length of the short time FFT. If `None`, it is set to `win_length//4`. Defaults to None. win_length (Optional[int], optional): The window length of the short time FFT. If `None`, it is set to same as `n_fft`. Defaults to None. window (str, optional): The window function applied to the signal before the Fourier transform. Supported window functions: 'hamming', 'hann', 'gaussian', 'exponential', 'triang', 'bohman', 'blackman', 'cosine', 'tukey', 'taylor', 'bartlett', 'kaiser', 'nuttall'. Defaults to 'hann'. power (float, optional): Exponent for the magnitude spectrogram. Defaults to 2.0. center (bool, optional): Whether to pad `x` to make that the :math:`t imes hop\_length` at the center of `t`-th frame. Defaults to True. pad_mode (str, optional): Choose padding pattern when `center` is `True`. Defaults to 'reflect'. n_mels (int, optional): Number of mel bins. Defaults to 64. f_min (float, optional): Minimum frequency in Hz. Defaults to 50.0. f_max (Optional[float], optional): Maximum frequency in Hz. Defaults to None. htk (bool, optional): Use HTK formula in computing fbank matrix. Defaults to False. norm (Union[str, float], optional): Type of normalization in computing fbank matrix. Slaney-style is used by default. You can specify norm=1.0/2.0 to use customized p-norm normalization. Defaults to 'slaney'. ref_value (float, optional): The reference value. If smaller than 1.0, the db level of the signal will be pulled up accordingly. Otherwise, the db level is pushed down. Defaults to 1.0. amin (float, optional): The minimum value of input magnitude. Defaults to 1e-10. top_db (Optional[float], optional): The maximum db value of spectrogram. Defaults to None. dtype (str, optional): Data type of input and window. Defaults to 'float32'. Returns: :ref:`api_paddle_nn_Layer`. An instance of MFCC. Examples: .. code-block:: python >>> import paddle >>> from paddle.audio.features import MFCC >>> sample_rate = 16000 >>> wav_duration = 0.5 >>> num_channels = 1 >>> num_frames = sample_rate * wav_duration >>> wav_data = paddle.linspace(-1.0, 1.0, int(num_frames)) * 0.1 >>> waveform = wav_data.tile([num_channels, 1]) >>> feature_extractor = MFCC(sr=sample_rate, n_fft=512, window = 'hann') >>> feats = feature_extractor(waveform) r dct_matrixc>[TU]5 X*::d SUSU 35e[S0SU_SU_SU_SU_SU_SU_S U_S U _S U _S U _S U _SU _SU_SU_SU_SU_SU_6Ul[ X*US9UlUR SUR 5 g)Nz%n_mfcc cannot be larger than n_mels: z vs r`r&r'r(r)r!r*r+rXrYrZr[r]rqrrrsr%)n_mfccrXr%r})r,r-ro_log_melspectrogramr r}r2)r3r`rr&r'r(r)r!r*r+rXrYrZr[r]rqrrrsr%r4s r5r- MFCC.__init__s *  3F84x H $5$ $ $ "$ " $  $  $ $ $ $ $ $ $ $  $ $ !$ "#$  &%FO \4??;r7cURU5n[R"URS5UR5RS5nU$)z Args: x (Tensor): Tensor of waveforms with shape `(N, T)` Returns: Tensor: Mel frequency cepstral coefficients with shape `(N, n_mfcc, num_frames)`. )rr )rr.rd transposer})r3r;rxmfccs r5r= MFCC.forwardsJ2215}}  % %i 0$// )I   r7)rr})rh(r?NNrriTrArjrkNFrlr@rzNrB)&r`rCrrCr&rCr'rDr(rDr)rr!r r*rEr+rFrXrCrYr rZrmr[rEr]r\rqr rrr rsrmr%rGrHrIrJrKrTs@r5r|r|Zs(T!%!%!''0"*2#'-< -<-< -<  -<  -<-<-<-<%-<-<-<-<-<(-< !-<"#-<$%-<&'-<( )-<-<^  r7r|) __future__r functoolsrtypingrrtyping_extensionsrr.r functionalr r r functional.windowr rrrQLayerrrVror|rr7r5rs#)' FF*#  "R"((RjhRXXhVhhVh288hr7