Spectrogram Transform

class Spectrogram[source]

Spectrogram(n_fft:listified[int]=1024, win_length:listified[int] | None=None, hop_length:listified[int] | None=None, pad:listified[int]=0, window_fn:listified[Callable[..., Tensor]]=hann_window, power:listified[float]=2.0, normalized:listified[bool]=False, wkwargs:listified[dict] | None=None, center:listified[bool]=True, pad_mode:listified[str]='reflect', onesided:listified[bool]=True, norm:listified[str] | None=None) :: DisplayedTransform

Convert a TensorAudio into one or more TensorSpec

Mel Transform

class MelSpectrogram[source]

MelSpectrogram(sample_rate:listified[int]=16000, n_fft:listified[int]=1024, win_length:listified[int] | None=None, hop_length:listified[int] | None=None, f_min:listified[float]=0.0, f_max:listified[float] | None=None, pad:listified[int]=0, n_mels:listified[int]=128, window_fn:listified[Callable[..., Tensor]]=hann_window, power:listified[float]=2.0, normalized:listified[bool]=False, wkwargs:listified[dict] | None=None, center:listified[bool]=True, pad_mode:listified[str]='reflect', onesided:listified[bool]=True, norm:listified[str] | None=None, mel_scale:listified[str]='htk') :: DisplayedTransform

Convert a TensorAudio into one or more TensorMelSpec

TransformBlocks for audio

AudioBlock[source]

AudioBlock()

A TransformBlock for audio of cls

SpecBlock[source]

SpecBlock(n_fft:listified[int]=1024, win_length:listified[int] | None=None, hop_length:listified[int] | None=None, pad:listified[int]=0, window_fn:listified[Callable[..., Tensor]]=hann_window, power:listified[float]=2.0, normalized:listified[bool]=False, wkwargs:listified[dict] | None=None, center:listified[bool]=True, pad_mode:listified[str]='reflect', onesided:listified[bool]=True, norm:listified[str] | None=None)

A TransformBlock to read TensorAudio and then use the GPU to turn audio into one or more Spectrograms

	Type	Default	Details
n_fft	listified[int]	1024	Spectrogram args
win_length	listified[int] or None	None	No Content
hop_length	listified[int] or None	None	No Content
pad	listified[int]	0	No Content
window_fn	listified[Callable[..., Tensor]]	_VariableFunctionsClass.hann_window	No Content
power	listified[float]	2.0	No Content
normalized	listified[bool]	False	No Content
wkwargs	listified[dict] or None	None	No Content
center	listified[bool]	True	No Content
pad_mode	listified[str]	reflect	No Content
onesided	listified[bool]	True	No Content
norm	listified[str] or None	None	No Content

MelSpecBlock[source]

MelSpecBlock(sr:listified[int]=16000, n_fft:listified[int]=1024, win_length:listified[int] | None=None, hop_length:listified[int] | None=None, f_min:listified[float]=0.0, f_max:listified[float] | None=None, pad:listified[int]=0, n_mels:listified[int]=128, window_fn:listified[Callable[..., Tensor]]=hann_window, power:listified[float]=2.0, normalized:listified[bool]=False, wkwargs:listified[dict] | None=None, center:listified[bool]=True, pad_mode:listified[str]='reflect', onesided:listified[bool]=True, norm:listified[str] | None=None, mel_scale:listified[str]='htk')

A TransformBlock to read TensorAudio and then use the GPU to turn audio into one or more MelSpectrograms

	Type	Default	Details
sr	listified[int]	16000	MelSpectrogram args
n_fft	listified[int]	1024	No Content
win_length	listified[int] or None	None	No Content
hop_length	listified[int] or None	None	No Content
f_min	listified[float]	0.0	No Content
f_max	listified[float] or None	None	No Content
pad	listified[int]	0	No Content
n_mels	listified[int]	128	No Content
window_fn	listified[Callable[..., Tensor]]	_VariableFunctionsClass.hann_window	No Content
power	listified[float]	2.0	No Content
normalized	listified[bool]	False	No Content
wkwargs	listified[dict] or None	None	No Content
center	listified[bool]	True	No Content
pad_mode	listified[str]	reflect	No Content
onesided	listified[bool]	True	No Content
norm	listified[str] or None	None	No Content
mel_scale	listified[str]	htk	No Content