Spaces:
Running
Running
File size: 1,914 Bytes
35c1cfd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# MIT License
#
# Copyright 2023 ByteDance Inc.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”),
# to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
# IN THE SOFTWARE.
import torchaudio
from torch import nn
class MelSTFT(nn.Module):
def __init__(
self,
sample_rate=24000,
n_fft=2048,
hop_length=240,
n_mels=128,
is_db=False,
):
super(MelSTFT, self).__init__()
# spectrogram
self.mel_stft = torchaudio.transforms.MelSpectrogram(
sample_rate=sample_rate, n_fft=n_fft, hop_length=hop_length, n_mels=n_mels
)
# amplitude to decibel
self.is_db = is_db
if is_db:
self.amplitude_to_db = torchaudio.transforms.AmplitudeToDB()
def forward(self, waveform):
if self.is_db:
return self.amplitude_to_db(self.mel_stft(waveform))
else:
return self.mel_stft(waveform)
|