layers.TacotronSTFT Class Reference

Inheritance diagram for layers.TacotronSTFT:

Collaboration diagram for layers.TacotronSTFT:

Public Member Functions
def	__init__ (self, filter_length=1024, hop_length=256, win_length=1024, n_mel_channels=80, sampling_rate=22050, mel_fmin=0.0, mel_fmax=8000.0)
def	spectral_normalize (self, magnitudes)
def	spectral_de_normalize (self, magnitudes)
def	mel_spectrogram (self, y)

Public Attributes
	n_mel_channels
	sampling_rate
	stft_fn

Constructor & Destructor Documentation

__init__()

def layers.TacotronSTFT.__init__	(		self,
			filter_length = 1024,
			hop_length = 256,
			win_length = 1024,
			n_mel_channels = 80,
			sampling_rate = 22050,
			mel_fmin = 0.0,
			mel_fmax = 8000.0
	)

Member Function Documentation

spectral_normalize()

def layers.TacotronSTFT.spectral_normalize	(		self,
			magnitudes
	)

Here is the caller graph for this function:

spectral_de_normalize()

def layers.TacotronSTFT.spectral_de_normalize	(		self,
			magnitudes
	)

mel_spectrogram()

def layers.TacotronSTFT.mel_spectrogram	(		self,
			y
	)

Computes mel-spectrograms from a batch of waves
PARAMS
------
y: Variable(torch.FloatTensor) with shape (B, T) in range [-1, 1]

RETURNS
-------
mel_output: torch.FloatTensor of shape (B, n_mel_channels, T)

Here is the call graph for this function:

Member Data Documentation

n_mel_channels

layers.TacotronSTFT.n_mel_channels

sampling_rate

layers.TacotronSTFT.sampling_rate

stft_fn

layers.TacotronSTFT.stft_fn

---

The documentation for this class was generated from the following file:

• layers.py