bacow/GPT-SoVITS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

Browse Source 
* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
This commit is contained in:
XXXXRT666
2025-04-07 09:42:47 +01:00
committed by GitHub
parent 9da7e17efe
commit 53cac93589
132 changed files with 8185 additions and 6648 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
GPT_SoVITS/module/mel_processing.py
View File

@@ -1,16 +1,5 @@
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
@@ -58,9 +47,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
dtype_device = str(y.dtype) + "_" + str(y.device)
wnsize_dtype_device = str(win_size) + "_" + dtype_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
)
hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(dtype=y.dtype, device=y.device)
y = torch.nn.functional.pad(
y.unsqueeze(1),
@@ -90,20 +77,14 @@ def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
dtype_device = str(spec.dtype) + "_" + str(spec.device)
fmax_dtype_device = str(fmax) + "_" + dtype_device
if fmax_dtype_device not in mel_basis:
mel = librosa_mel_fn(
sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax
)
mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
dtype=spec.dtype, device=spec.device
)
mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=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
def mel_spectrogram_torch(
y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False
):
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:
@@ -114,16 +95,10 @@ def mel_spectrogram_torch(
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(
sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax
)
mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
dtype=y.dtype, device=y.device
)
mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=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
)
hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(dtype=y.dtype, device=y.device)
y = torch.nn.functional.pad(
y.unsqueeze(1),