pytorch来处理音频数据流程

系列文章目录

提示：这里可以添加系列文章的所有文章的目录，目录需要自己手动添加
例如：第一章 Python 机器学习入门之pandas的使用

---

提示：写完文章后，目录可以自动生成，如何生成可参考右边的帮助文档

---

前言

pytorch音频数据处理流程

---

一、引入必要的库和GPU

%matplotlib inline
!pip install torch==1.7.0+cu101 torchvision==0.8.1+cu101 torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchaudio

import matplotlib.pyplot as plt
import IPython.display as ipd
from tqdm.notebook import tqdm
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

from torchaudio.datasets import SPEECHCOMMANDS
import os

二、加载所需要的数据集合

数据集的格式说明

数据集合的组织形式各种各样，但是最终读入DataSet的格式是一样的，提供一种数据集组织格式

-数据类型一
------- 1.wav
--------2.wav
--------3.wav
-数据类型二
------- 1.wav
--------2.wav
--------3.wav
test.txt(保存的数据文件路径)
train.txt(保存了数据文件的路径)

构建Dataset（+transforms）

FOLDER_IN_ARCHIVE = "SpeechCommands"
URL = "speech_commands_v0.02"
HASH_DIVIDER = "_nohash_"
EXCEPT_FOLDER = "_background_noise_"
_CHECKSUMS = {
   
    "https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.01.tar.gz":
    "3cd23799cb2bbdec517f1cc028f8d43c",
    "https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz":
    "6b74f3901214cb2c2934e98196829835",
}


def load_speechcommands_item(filepath: str, path: str) -> Tuple[Tensor, int, str, str, int]:
    relpath = os.path.relpath(filepath, path)
    label, filename = os.path.split(relpath)
    speaker, _ = os.path.splitext(filename)

    speaker_id, utterance_number = speaker.split(HASH_DIVIDER)
    utterance_number = int(utterance_number)

    # Load audio
    waveform, sample_rate = torchaudio.load(filepath)
    return waveform, sample_rate, label, speaker_id, utterance_number
class SPEECHCOMMANDS(Dataset):
    """Create a Dataset for Speech Commands.

    Args:
        root (str): Path to the directory where the dataset is found or downloaded.
        url (str, optional): The URL to download the dataset from,
            or the type of the dataset to dowload.
            Allowed type values are ``"speech_commands_v0.01"`` and ``"speech_commands_v0.02"``
            (default: ``"speech_commands_v0.02"``)
        folder_in_archive (str, optional):
            The top-level directory of the dataset. (default: ``"SpeechCommands"``)
        download (bool, optional):
            Whether to download the dataset if it is not found at root path. (default: ``False``).
    """

    def __init__(self,
                 root: str,
                 url: str = URL,
                 folder_in_archive: str = FOLDER_IN_ARCHIVE,
                 download: bool = False) -> None:
        if url in [
            "speech_commands_v0.01",
            "speech_commands_v0.02",
        ]:
            base_url = "https://storage.googleapis.com/download.tensorflow.org/data/"
            ext_archive = ".tar.gz"

            url = os.path.join(base_url, url + ext_archive)

        basename = os.path.basename(url)
        archive = os.path.join(root, basename)

        basename = basename.rsplit(".", 2)[0]
        folder_in_archive = os.path.join(folder_in_archive, basename)

        self._path = os.path.join(root, folder_in_archive)

        if download:
            if not os.path.isdir(self._path):
                if not os.path.isfile(archive):
                    checksum = _CHECKSUMS.get(url, None)
                    download_url(url, root, hash_value=checksum, hash_type="md5"