From 329d739e70dea7f0708f8538b985c4a39a999480 Mon Sep 17 00:00:00 2001 From: tarepan Date: Mon, 24 Apr 2023 12:45:20 +0900 Subject: [PATCH] Refactor mel module (#132) * Refactor wave-to-mel * Add docstring on mel * Refactor mel module import and variable names --- train/mel_processing.py | 108 ++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 70 deletions(-) diff --git a/train/mel_processing.py b/train/mel_processing.py index 315b3d1..0c1867b 100644 --- a/train/mel_processing.py +++ b/train/mel_processing.py @@ -1,18 +1,8 @@ -import math -import os -import random import torch -from torch import nn -import torch.nn.functional as F import torch.utils.data -import numpy as np -import librosa -import librosa.util as librosa_util -from librosa.util import normalize, pad_center, tiny -from scipy.signal import get_window -from scipy.io.wavfile import read from librosa.filters import mel as librosa_mel_fn + MAX_WAV_VALUE = 32768.0 @@ -35,25 +25,38 @@ def dynamic_range_decompression_torch(x, C=1): def spectral_normalize_torch(magnitudes): - output = dynamic_range_compression_torch(magnitudes) - return output + return dynamic_range_compression_torch(magnitudes) def spectral_de_normalize_torch(magnitudes): - output = dynamic_range_decompression_torch(magnitudes) - return output + return dynamic_range_decompression_torch(magnitudes) +# Reusable banks mel_basis = {} hann_window = {} def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False): + """Convert waveform into Linear-frequency Linear-amplitude spectrogram. + + Args: + y :: (B, T) - Audio waveforms + n_fft + sampling_rate + hop_size + win_size + center + Returns: + :: (B, Freq, Frame) - Linear-frequency Linear-amplitude spectrogram + """ + # Validation if torch.min(y) < -1.0: print("min value is ", torch.min(y)) if torch.max(y) > 1.0: print("max value is ", torch.max(y)) + # Window - Cache if needed global hann_window dtype_device = str(y.dtype) + "_" + str(y.device) wnsize_dtype_device = str(win_size) + "_" + dtype_device @@ -62,6 +65,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False) dtype=y.dtype, device=y.device ) + # Padding y = torch.nn.functional.pad( y.unsqueeze(1), (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)), @@ -69,6 +73,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False) ) y = y.squeeze(1) + # Complex Spectrogram :: (B, T) -> (B, Freq, Frame, RealComplex=2) spec = torch.stft( y, n_fft, @@ -82,11 +87,13 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False) return_complex=False, ) + # Linear-frequency Linear-amplitude spectrogram :: (B, Freq, Frame, RealComplex=2) -> (B, Freq, Frame) spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6) return spec def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax): + # MelBasis - Cache if needed global mel_basis dtype_device = str(spec.dtype) + "_" + str(spec.device) fmax_dtype_device = str(fmax) + "_" + dtype_device @@ -95,66 +102,27 @@ def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax): mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to( dtype=spec.dtype, device=spec.device ) - spec = torch.matmul(mel_basis[fmax_dtype_device], spec) - spec = spectral_normalize_torch(spec) - return spec + + # Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame) + melspec = torch.matmul(mel_basis[fmax_dtype_device], spec) + melspec = spectral_normalize_torch(melspec) + return melspec def mel_spectrogram_torch( y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False ): - if torch.min(y) < -1.0: - print("min value is ", torch.min(y)) - if torch.max(y) > 1.0: - print("max value is ", torch.max(y)) + """Convert waveform into Mel-frequency Log-amplitude spectrogram. - global mel_basis, hann_window - dtype_device = str(y.dtype) + "_" + str(y.device) - fmax_dtype_device = str(fmax) + "_" + dtype_device - wnsize_dtype_device = str(win_size) + "_" + dtype_device - if fmax_dtype_device not in mel_basis: - mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax) - mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to( - dtype=y.dtype, device=y.device - ) - if wnsize_dtype_device not in hann_window: - hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to( - dtype=y.dtype, device=y.device - ) + Args: + y :: (B, T) - Waveforms + Returns: + melspec :: (B, Freq, Frame) - Mel-frequency Log-amplitude spectrogram + """ + # Linear-frequency Linear-amplitude spectrogram :: (B, T) -> (B, Freq, Frame) + spec = spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center) - y = torch.nn.functional.pad( - y.unsqueeze(1), - (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)), - mode="reflect", - ) - y = y.squeeze(1) + # Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame) + melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax) - # spec = torch.stft( - # y, - # n_fft, - # hop_length=hop_size, - # win_length=win_size, - # window=hann_window[wnsize_dtype_device], - # center=center, - # pad_mode="reflect", - # normalized=False, - # onesided=True, - # ) - spec = torch.stft( - y, - n_fft, - hop_length=hop_size, - win_length=win_size, - window=hann_window[wnsize_dtype_device], - center=center, - pad_mode="reflect", - normalized=False, - onesided=True, - return_complex=False, - ) - spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6) - - spec = torch.matmul(mel_basis[fmax_dtype_device], spec) - spec = spectral_normalize_torch(spec) - - return spec + return melspec