utils.py

import numpy as np
from scipy.io.wavfile import read
import torch


def get_mask_from_lengths(lengths):
    max_len = torch.max(lengths).item()
    ids = torch.arange(0, max_len, out=torch.cuda.LongTensor(max_len))
    mask = (ids < lengths.unsqueeze(1))
    return mask

def get_mask_from_lengths2(lengths):
    max_len = lengths[0].item()
    ids = torch.arange(0, max_len, out=torch.cuda.LongTensor(max_len))
    mask = (ids < lengths.unsqueeze(1))
    return mask

def load_wav_to_torch(full_path):
    sampling_rate, data = read(full_path)
    return torch.FloatTensor(data.astype(np.float32)), sampling_rate


def load_filepaths_and_text(filename, split="|"):
    with open(filename, encoding='utf-8') as f:
        filepaths_and_text = [line.strip().split(split) for line in f]
    return filepaths_and_text


def to_gpu(x):
    x = x.contiguous()

    if torch.cuda.is_available():
        x = x.cuda(non_blocking=True)
    return torch.autograd.Variable(x)

def get_sinusoid_encoding_table(n_position, d_hid, padding_idx=None):
    ''' Sinusoid position encoding table '''

    def cal_angle(position, hid_idx):
        return position / np.power(10000, 2 * (hid_idx // 2) / d_hid)

    def get_posi_angle_vec(position):
        return [cal_angle(position, hid_j) for hid_j in range(d_hid)]

    sinusoid_table = np.array([get_posi_angle_vec(pos_i) for pos_i in range(n_position)])

    sinusoid_table[:, 0::2] = np.sin(sinusoid_table[:, 0::2])  # dim 2i
    sinusoid_table[:, 1::2] = np.cos(sinusoid_table[:, 1::2])  # dim 2i+1

    if padding_idx is not None:
        # zero vector for padding dimension
        sinusoid_table[padding_idx] = 0.

    return torch.FloatTensor(sinusoid_table)