VctkDataLoaderOptions

Options & Configuration · AiDotNet.Data.Audio.Benchmarks

Configuration for the VCTK Corpus 0.92 multi-speaker TTS loader (Yamagishi et al. 2019).

How It Works

VCTK — 110 English speakers × ~400 utterances each (~44 hours) at 48 kHz. Standard multi-speaker TTS / voice-cloning corpus.

Constructors

Constructor Summary
VctkDataLoaderOptions()

Properties

Property Summary
DatasetSplit Split { get; set; } Gets or sets which split of the dataset is loaded.
bool AutoDownload { get; set; } Gets or sets whether the dataset is downloaded into the data directory when it is not there.
int MaxAudioSamples { get; set; } Gets or sets the waveform length, in samples, each clip is zero-padded or truncated to.
int MaxTextLength { get; set; } Gets or sets the token length each transcript is padded or truncated to.
int VocabularySize { get; set; } Gets or sets the most distinct tokens in the vocabulary built from the loaded text.
int? MaxSamples { get; set; } Gets or sets the most samples loaded; null loads the whole split.
string DataPath { get; set; } Gets or sets the dataset root directory; null uses the default data directory for this dataset.
string SpeakerFilter { get; set; } Comma-separated speaker-ID filter (e.g.

Methods

Method Summary
void Validate() Validates that all option values are within acceptable ranges.