Shortcuts

Source code for torchaudio.datasets.libritts

import os
from typing import Tuple, Union
from pathlib import Path

import torchaudio
from torch import Tensor
from torch.utils.data import Dataset
from torchaudio.datasets.utils import (
    download_url,
    extract_archive,
)

URL = "train-clean-100"
FOLDER_IN_ARCHIVE = "LibriTTS"
_CHECKSUMS = {
    "http://www.openslr.org/60/dev-clean.tar.gz": "0c3076c1e5245bb3f0af7d82087ee207",
    "http://www.openslr.org/60/dev-other.tar.gz": "815555d8d75995782ac3ccd7f047213d",
    "http://www.openslr.org/60/test-clean.tar.gz": "7bed3bdb047c4c197f1ad3bc412db59f",
    "http://www.openslr.org/60/test-other.tar.gz": "ae3258249472a13b5abef2a816f733e4",
    "http://www.openslr.org/60/train-clean-100.tar.gz": "4a8c202b78fe1bc0c47916a98f3a2ea8",
    "http://www.openslr.org/60/train-clean-360.tar.gz": "a84ef10ddade5fd25df69596a2767b2d",
    "http://www.openslr.org/60/train-other-500.tar.gz": "7b181dd5ace343a5f38427999684aa6f",
}


def load_libritts_item(
    fileid: str,
    path: str,
    ext_audio: str,
    ext_original_txt: str,
    ext_normalized_txt: str,
) -> Tuple[Tensor, int, str, str, int, int, str]:
    speaker_id, chapter_id, segment_id, utterance_id = fileid.split("_")
    utterance_id = fileid

    normalized_text = utterance_id + ext_normalized_txt
    normalized_text = os.path.join(path, speaker_id, chapter_id, normalized_text)

    original_text = utterance_id + ext_original_txt
    original_text = os.path.join(path, speaker_id, chapter_id, original_text)

    file_audio = utterance_id + ext_audio
    file_audio = os.path.join(path, speaker_id, chapter_id, file_audio)

    # Load audio
    waveform, sample_rate = torchaudio.load(file_audio)

    # Load original text
    with open(original_text) as ft:
        original_text = ft.readline()

    # Load normalized text
    with open(normalized_text, "r") as ft:
        normalized_text = ft.readline()

    return (
        waveform,
        sample_rate,
        original_text,
        normalized_text,
        int(speaker_id),
        int(chapter_id),
        utterance_id,
    )


[docs]class LIBRITTS(Dataset): """Create a Dataset for LibriTTS. Args: root (str or Path): 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 ``"dev-clean"``, ``"dev-other"``, ``"test-clean"``, ``"test-other"``, ``"train-clean-100"``, ``"train-clean-360"`` and ``"train-other-500"``. (default: ``"train-clean-100"``) folder_in_archive (str, optional): The top-level directory of the dataset. (default: ``"LibriTTS"``) download (bool, optional): Whether to download the dataset if it is not found at root path. (default: ``False``). """ _ext_original_txt = ".original.txt" _ext_normalized_txt = ".normalized.txt" _ext_audio = ".wav" def __init__( self, root: Union[str, Path], url: str = URL, folder_in_archive: str = FOLDER_IN_ARCHIVE, download: bool = False, ) -> None: if url in [ "dev-clean", "dev-other", "test-clean", "test-other", "train-clean-100", "train-clean-360", "train-other-500", ]: ext_archive = ".tar.gz" base_url = "http://www.openslr.org/resources/60/" url = os.path.join(base_url, url + ext_archive) # Get string representation of 'root' in case Path object is passed root = os.fspath(root) basename = os.path.basename(url) archive = os.path.join(root, basename) basename = basename.split(".")[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) extract_archive(archive) self._walker = sorted(str(p.stem) for p in Path(self._path).glob('*/*/*' + self._ext_audio))
[docs] def __getitem__(self, n: int) -> Tuple[Tensor, int, str, str, int, int, str]: """Load the n-th sample from the dataset. Args: n (int): The index of the sample to be loaded Returns: (Tensor, int, str, str, str, int, int, str): ``(waveform, sample_rate, original_text, normalized_text, speaker_id, chapter_id, utterance_id)`` """ fileid = self._walker[n] return load_libritts_item( fileid, self._path, self._ext_audio, self._ext_original_txt, self._ext_normalized_txt, )
def __len__(self) -> int: return len(self._walker)

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources