Spaces:
Running
Running
File size: 1,575 Bytes
67c46fd |
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 52 53 54 55 56 |
import os
import json
import torch
import logging
import concurrent.futures
import librosa
import torch.distributed as dist
from typing import Collection
import torch
import torchaudio
from torch import nn
import random
import re
from funasr_detach.tokenizer.cleaner import TextCleaner
from funasr_detach.register import tables
@tables.register("preprocessor_classes", "SpeechPreprocessSpeedPerturb")
class SpeechPreprocessSpeedPerturb(nn.Module):
def __init__(self, speed_perturb: list = None, **kwargs):
super().__init__()
self.speed_perturb = speed_perturb
def forward(self, waveform, fs, **kwargs):
if self.speed_perturb is None:
return waveform
speed = random.choice(self.speed_perturb)
if speed != 1.0:
if not isinstance(waveform, torch.Tensor):
waveform = torch.tensor(waveform)
waveform, _ = torchaudio.sox_effects.apply_effects_tensor(
waveform.view(1, -1), fs, [["speed", str(speed)], ["rate", str(fs)]]
)
waveform = waveform.view(-1)
return waveform
@tables.register("preprocessor_classes", "TextPreprocessSegDict")
class TextPreprocessSegDict(nn.Module):
def __init__(
self,
seg_dict: str = None,
text_cleaner: Collection[str] = None,
split_with_space: bool = False,
**kwargs
):
super().__init__()
self.text_cleaner = TextCleaner(text_cleaner)
def forward(self, text, **kwargs):
text = self.text_cleaner(text)
return text
|