The path/URL to load the audio from.

The sampling rate to use when decoding the audio.

The length of the Hanning window to generate.

Number of frequencies used to compute the spectrogram (should be the same as in stft).

Number of mel filters to generate.

Lowest frequency of interest in Hz.

Highest frequency of interest in Hz. This should not exceed sampling_rate / 2.

Sample rate of the audio waveform.

If "slaney", divide the triangular mel weights by the width of the mel band (area normalization).

The mel frequency scale to use, "htk" or "slaney".

If this option is enabled, the triangular filter is applied in mel space rather than frequency space. This should be set to true in order to get the same results as torchaudio when computing mel filters.

The input waveform of shape (length,). This must be a single real-valued, mono waveform.

The windowing function to apply of shape (frame_length,), including zero-padding if necessary. The actual window length may be shorter than frame_length, but we're assuming the array has already been zero-padded.

The length of the analysis frames in samples (a.k.a., fft_length).

The stride between successive analysis frames in samples.

The size of the FFT buffer in samples. This determines how many frequency bins the spectrogram will have. For optimal speed, this should be a power of two. If null, uses frame_length.

If 1.0, returns the amplitude spectrogram. If 2.0, returns the power spectrogram. If null, returns complex numbers.

Whether to pad the waveform so that frame t is centered around time t * hop_length. If false, frame t will start at time t * hop_length.

Padding mode used when center is true. Possible values are: "constant" (pad with zeros), "edge" (pad with edge values), "reflect" (pads with mirrored values).

If true, only computes the positive frequencies and returns a spectrogram containing fft_length // 2 + 1 frequency bins. If false, also computes the negative frequencies and returns fft_length frequency bins.

Coefficient for a low-pass filter that applies pre-emphasis before the DFT.

The mel filter bank of shape (num_freq_bins, num_mel_filters). If supplied, applies this filter bank to create a mel spectrogram.

Minimum value of mel frequency banks.

How to convert the spectrogram to log scale. Possible options are: null (don't convert), "log" (take the natural logarithm) "log10" (take the base-10 logarithm), "dB" (convert to decibels). Can only be used when power is not null.

Sets the input spectrogram value that corresponds to 0 dB. For example, use max(spectrogram)[0] to set the loudest part to 0 dB. Must be greater than zero.

The spectrogram will be clipped to this minimum value before conversion to decibels, to avoid taking log(0). For a power spectrogram, the default of 1e-10 corresponds to a minimum of -100 dB. For an amplitude spectrogram, the value 1e-5 corresponds to -100 dB. Must be greater than zero.

Sets the maximum dynamic range in decibels. For example, if db_range = 80, the difference between the peak value and the smallest value will never be more than 80 dB. Must be greater than zero.

Subtract mean from waveform on each frame, applied before pre-emphasis. This should be set to true in order to get the same results as torchaudio.compliance.kaldi.fbank when computing mel filters.

If provided, limits the number of frames to compute to this value.

If true, pads the output spectrogram to have max_num_frames frames.

If true, the returned spectrogram will have shape (num_frames, num_frequency_bins/num_mel_filters). If false, the returned spectrogram will have shape (num_frequency_bins/num_mel_filters, num_frames).

The length of the window in samples.

The name of the window function.

Additional options.

Whether the window is periodic or symmetric.

The length of the analysis frames in samples. Provide a value for frame_length if the window is smaller than the frame length, so that it will be zero-padded.

Whether to center the window inside the FFT buffer. Only used when frame_length is provided.

Discrete frequencies of the FFT bins in Hz, of shape (num_frequency_bins,).

Center frequencies of the triangular filters to create, in Hz, of shape (num_mel_filters,).

The starting value of the sequence.

The end value of the sequence.

Number of samples to generate.

The array to pad.

The amount of padding to add to the left.

The amount of padding to add to the right.

The input amplitude (mel) spectrogram.

Sets the input spectrogram value that corresponds to 0 dB. For example, use np.max(spectrogram) to set the loudest part to 0 dB. Must be greater than zero.

The spectrogram will be clipped to this minimum value before conversion to decibels, to avoid taking log(0). The default of 1e-5 corresponds to a minimum of -100 dB. Must be greater than zero.

Sets the maximum dynamic range in decibels. For example, if db_range = 80, the difference between the peak value and the smallest value will never be more than 80 dB. Must be greater than zero.

The input power (mel) spectrogram. Note that a power spectrogram has the amplitudes squared!

Sets the input spectrogram value that corresponds to 0 dB. For example, use np.max(spectrogram) to set the loudest part to 0 dB. Must be greater than zero.

The spectrogram will be clipped to this minimum value before conversion to decibels, to avoid taking log(0). The default of 1e-10 corresponds to a minimum of -100 dB. Must be greater than zero.

Sets the maximum dynamic range in decibels. For example, if db_range = 80, the difference between the peak value and the smallest value will never be more than 80 dB. Must be greater than zero.