beginner/audio_datasets_tutorial

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

오디오 데이터셋

저자: Moto Hira 번역: 백승엽

``torchaudio``는 공용으로 접근할 수 있는 일반적인 데이터셋에 쉽게 접근할 수 있는 기능을 제공합니다. 사용할 수 있는 데이터셋 목록은 공식 문서를 참고하세요.

import torch
import torchaudio

print(torch.__version__)
print(torchaudio.__version__)

2.8.0+cu128
2.8.0+cu128

import os

import IPython

import matplotlib.pyplot as plt


_SAMPLE_DIR = "_assets"
YESNO_DATASET_PATH = os.path.join(_SAMPLE_DIR, "yes_no")
os.makedirs(YESNO_DATASET_PATH, exist_ok=True)


def plot_specgram(waveform, sample_rate, title="Spectrogram"):
    waveform = waveform.numpy()

    figure, ax = plt.subplots()
    ax.specgram(waveform[0], Fs=sample_rate)
    figure.suptitle(title)
    figure.tight_layout()

여기서 torchaudio.datasets.YESNO 데이터셋의 사용 방법을 볼 수 있습니다.

dataset = torchaudio.datasets.YESNO(YESNO_DATASET_PATH, download=True)

  0%|          | 0.00/4.49M [00:00<?, ?B/s]
  3%|▎         | 128k/4.49M [00:00<00:25, 181kB/s]
  6%|▌         | 256k/4.49M [00:00<00:14, 298kB/s]
 11%|█         | 512k/4.49M [00:01<00:07, 546kB/s]
 20%|█▉        | 896k/4.49M [00:01<00:04, 889kB/s]
 42%|████▏     | 1.88M/4.49M [00:01<00:01, 1.94MB/s]
 81%|████████  | 3.62M/4.49M [00:01<00:00, 3.68MB/s]
100%|██████████| 4.49M/4.49M [00:01<00:00, 2.41MB/s]

i = 1
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)

/opt/conda/lib/python3.11/site-packages/torchaudio/_backend/utils.py:213: UserWarning:

In 2.9, this function's implementation will be changed to use torchaudio.load_with_torchcodec` under the hood. Some parameters like ``normalize``, ``format``, ``buffer_size``, and ``backend`` will be ignored. We recommend that you port your code to rely directly on TorchCodec's decoder instead: https://docs.pytorch.org/torchcodec/stable/generated/torchcodec.decoders.AudioDecoder.html#torchcodec.decoders.AudioDecoder.

/opt/conda/lib/python3.11/site-packages/torchaudio/_backend/ffmpeg.py:88: UserWarning:

torio.io._streaming_media_decoder.StreamingMediaDecoder has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.

i = 3
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)

i = 5
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)

i = 5
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)

• 
•