paddlespeech.t2s.datasets package

Submodules

• paddlespeech.t2s.datasets.am_batch_fn module
  • ErnieSATCollateFn
  • build_erniesat_collate_fn()
  • erniesat_batch_fn()
  • fastspeech2_multi_spk_batch_fn()
  • fastspeech2_single_spk_batch_fn()
  • speedyspeech_multi_spk_batch_fn()
  • speedyspeech_single_spk_batch_fn()
  • tacotron2_multi_spk_batch_fn()
  • tacotron2_single_spk_batch_fn()
  • transformer_single_spk_batch_fn()
  • vits_multi_spk_batch_fn()
  • vits_single_spk_batch_fn()
• paddlespeech.t2s.datasets.batch module
  • SpecBatcher
  • TextIDBatcher
  • WavBatcher
  • batch_spec()
  • batch_text_id()
  • batch_wav()
• paddlespeech.t2s.datasets.data_table module
  • DataTable
• paddlespeech.t2s.datasets.dataset module
  • CacheDataset
  • ChainDataset
  • DictDataset
  • FilterDataset
  • SliceDataset
  • SubsetDataset
  • TransformDataset
  • TupleDataset
  • split()
• paddlespeech.t2s.datasets.get_feats module
  • Energy
    • Energy.get_energy()
  • LinearSpectrogram
    • LinearSpectrogram.get_linear_spectrogram()
  • LogMelFBank
    • LogMelFBank.get_log_mel_fbank()
  • Pitch
    • Pitch.get_pitch()
• paddlespeech.t2s.datasets.ljspeech module
  • LJSpeechMetaData
• paddlespeech.t2s.datasets.preprocess_utils module
  • compare_duration_and_mel_length()
  • get_input_token()
  • get_phn_dur()
  • get_phones_tones()
  • get_spk_id_map()
  • merge_silence()
• paddlespeech.t2s.datasets.sampler module
  • ErnieSATSampler
    • ErnieSATSampler.set_epoch()
• paddlespeech.t2s.datasets.vocoder_batch_fn module
  • Clip
  • WaveRNNClip
    • WaveRNNClip.to_quant()