File size: 1,654 Bytes
90f7c1e |
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 47 48 49 50 51 |
import numpy as np
import matplotlib.pyplot as plt
from scipy.io import wavfile
import torch
from torch.nn import functional as F
def repeat_expand_2d(content, target_len):
# align content with mel
src_len = content.shape[-1]
target = torch.zeros([content.shape[0], target_len], dtype=torch.float).to(content.device)
temp = torch.arange(src_len+1) * target_len / src_len
current_pos = 0
for i in range(target_len):
if i < temp[current_pos+1]:
target[:, i] = content[:, current_pos]
else:
current_pos += 1
target[:, i] = content[:, current_pos]
return target
def save_plot(tensor, savepath):
plt.style.use('default')
fig, ax = plt.subplots(figsize=(12, 3))
im = ax.imshow(tensor, aspect="auto", origin="lower", interpolation='none')
plt.colorbar(im, ax=ax)
plt.tight_layout()
fig.canvas.draw()
plt.savefig(savepath)
plt.close()
def save_audio(file_path, sampling_rate, audio):
audio = np.clip(audio.detach().cpu().squeeze().numpy(), -0.999, 0.999)
wavfile.write(file_path, sampling_rate, (audio * 32767).astype("int16"))
def minmax_norm_diff(tensor: torch.Tensor, vmax: float = 2.5, vmin: float = -12) -> torch.Tensor:
tensor = torch.clip(tensor, vmin, vmax)
tensor = 2 * (tensor - vmin) / (vmax - vmin) - 1
return tensor
def reverse_minmax_norm_diff(tensor: torch.Tensor, vmax: float = 2.5, vmin: float = -12) -> torch.Tensor:
tensor = torch.clip(tensor, -1.0, 1.0)
tensor = (tensor + 1) / 2
tensor = tensor * (vmax - vmin) + vmin
return tensor |