Datasets

TTS Dataset

class TTS.tts.datasets.TTSDataset(outputs_per_step=1, compute_linear_spec=False, ap=None, samples=None, tokenizer=None, compute_f0=False, compute_energy=False, f0_cache_path=None, energy_cache_path=None, return_wav=False, batch_group_size=0, min_text_len=0, max_text_len=inf, min_audio_len=0, max_audio_len=inf, phoneme_cache_path=None, precompute_num_workers=0, speaker_id_mapping=None, d_vector_mapping=None, language_id_mapping=None, use_noise_augment=False, start_by_longest=False, verbose=False)

collate_fn(batch)

Perform preprocessing and create a final data batch: 1. Sort batch instances by text-length 2. Convert Audio signal to features. 3. PAD sequences wrt r. 4. Load to Torch.

preprocess_samples()

Sort items based on text length or audio length in ascending order. Filter out samples out or the length range.

Vocoder Dataset

class TTS.vocoder.datasets.gan_dataset.GANDataset(ap, items, seq_len, hop_len, pad_short, conv_pad=2, return_pairs=False, is_training=True, return_segments=True, use_noise_augment=False, use_cache=False, verbose=False)

GAN Dataset searchs for all the wav files under root path and converts them to acoustic features on the fly and returns random segments of (audio, feature) couples.

load_item(idx)

load (audio, feat) couple

class TTS.vocoder.datasets.wavegrad_dataset.WaveGradDataset(ap, items, seq_len, hop_len, pad_short, conv_pad=2, is_training=True, return_segments=True, use_noise_augment=False, use_cache=False, verbose=False)

WaveGrad Dataset searchs for all the wav files under root path and converts them to acoustic features on the fly and returns random segments of (audio, feature) couples.

static collate_full_clips(batch)

This is used in tune_wavegrad.py. It pads sequences to the max length.

load_item(idx)

load (audio, feat) couple

load_test_samples(num_samples)

Return test samples.

Parameters:

num_samples (int) – Number of samples to return.

Returns:

melspectorgram and audio.

Return type:

List[Tuple]

Shapes

• melspectrogram (Tensor): \([C, T]\)

• audio (Tensor): \([T_audio]\)

class TTS.vocoder.datasets.wavernn_dataset.WaveRNNDataset(ap, items, seq_len, hop_len, pad, mode, mulaw, is_training=True, verbose=False, return_segments=True)

WaveRNN Dataset searchs for all the wav files under root path and converts them to acoustic features on the fly.

load_item(index)

load (audio, feat) couple if feature_path is set else compute it on the fly