MCPcopy Create free account

hub / github.com/MoonInTheRiver/DiffSinger / functions

Functions694 in github.com/MoonInTheRiver/DiffSinger

⨍ Functions 694◇ Types & classes 154
Functionget_lf0_cwt_norm
(f0s, mean, std)
utils/cwt.py:89
Methodget_path
Get hdf5 file path for a given key.
modules/parallel_wavegan/utils/utils.py:147
Functioninit_weights
(m, mean=0.0, std=0.01)
modules/hifigan/hifigan.py:14
Functionlibrosa_pad_lr
compute right padding (final frame) or both sides padding (first and final frames)
utils/audio.py:38
Functionlinear_beta_schedule
linear schedule
usr/diff/shallow_diffusion_tts.py:167
Functionload_ckpt
(cur_model, ckpt_base_dir, prefix_in_ckpt='model', force=True, strict=True)
utils/__init__.py:178
Functionload_wav
(full_path)
modules/hifigan/mel_utils.py:10
Functionload_wav
(wav_file, sr)
utils/cwt.py:7
Functionmake_positions
Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored.
utils/__init__.py:145
Functionmake_positions
Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored.
utils/tts_utils.py:6
Methodmax_positions
Maximum number of supported positions.
modules/commons/common_layers.py:145
Methodmel_denorm
(x)
modules/fastspeech/fs2.py:254
Methodmel_norm
(x)
modules/fastspeech/fs2.py:250
Functionmel_spectrogram
(y, hparams, center=False, complex=False)
modules/hifigan/mel_utils.py:45
Functionnormalize
(S, hparams)
utils/audio.py:55
Functionnormalize_cwt_lf0
(f0, mean, std)
utils/cwt.py:80
Functionnsw_test
()
utils/text_norm.py:718
Methodnum_gpus
(self)
utils/pl_utils.py:458
Methodnum_reserved_ids
(self)
utils/text_encoder.py:43
Functionnum_to_groups
(num, divisor)
usr/diff/diffusion.py:34
Functionnum_to_groups
(num, divisor)
usr/diff/shallow_diffusion_tts.py:34
Methodnum_tokens
(self, index)
tasks/base_task.py:51
Methodnum_workers
(self)
tasks/base_task.py:72
Methodon_before_zero_grad
(self, optimizer)
tasks/base_task.py:331
Methodon_epoch_end
(self)
tasks/base_task.py:162
Methodon_load_checkpoint
(self, checkpoint)
tasks/base_task.py:304
Methodoptimizer_closure
()
utils/pl_utils.py:1476
Methodoptimizer_step
(self, epoch, batch_idx, optimizer, optimizer_idx)
tasks/base_task.py:156
Methodout2mel
(self, x)
usr/diff/shallow_diffusion_tts.py:352
Methodoverride
(self, attrs)
usr/diff/net.py:21
Functionprint_arch
(model, model_name='model')
utils/__init__.py:240
Methodprocess
(cls, txt, pre_align_args)
data_gen/tts/txt_processors/base_text_processor.py:7
Methodprocess
(cls, txt, pre_align_args)
data_gen/tts/txt_processors/zh.py:26
Methodprocess_item
(cls, item_name, ph, txt, tg_fn, wav_fn, spk_id, encoder, binarization_args)
data_gen/singing/binarize.py:152
Methodprocess_item
(cls, item_name, ph, txt, tg_fn, wav_fn, spk_id, encoder, binarization_args)
data_gen/singing/binarize.py:237
Methodq_mean_variance
(self, x_start, t)
usr/diff/diffusion.py:229
Methodq_mean_variance
(self, x_start, t)
usr/diff/shallow_diffusion_tts.py:246
Methodreceptive_field_size
Return receptive field size.
modules/parallel_wavegan/models/parallel_wavegan.py:202
Functionregister_vocoder
(cls)
vocoders/base_vocoder.py:5
Functionremove_padding
(x, padding_idx=0)
utils/__init__.py:212
Methodremove_weight_norm
(self)
modules/hifigan/hifigan.py:89
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
modules/parallel_wavegan/models/parallel_wavegan.py:291
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
modules/parallel_wavegan/models/parallel_wavegan.py:425
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
modules/parallel_wavegan/models/melgan.py:395
Methodreset_parameters
Reset parameters.
modules/parallel_wavegan/layers/residual_block.py:22
Methodreset_parameters
Reset parameters.
modules/parallel_wavegan/layers/upsample.py:54
Methodsave_checkpoint
(self, filepath)
utils/pl_utils.py:739
Methodsave_result
(wav_out, mel, prefix, item_name, text, gen_dir, str_phs=None, mel2ph=None)
tasks/tts/fs2.py:449
Functionsave_wav
(wav, path, sr, norm=False)
utils/audio.py:12
Methodshuffle_batches
(batches)
tasks/tts/tts.py:57
Functionsilu
(x)
usr/diff/net.py:54
Functionsoftmax
(x, dim)
utils/__init__.py:160
Functionsoftmax
(x, dim)
utils/tts_utils.py:20
Methodsp_phonemes
()
data_gen/tts/txt_processors/base_text_processor.py:3
Methodspec2wav
(self, mel, **kwargs)
vocoders/hifigan.py:55
Methodspec2wav
:param mel: [T, 80] :return: wav: [T']
vocoders/base_vocoder.py:23
Functionspec_f0_to_figure
(spec, f0s, figsize=None)
utils/plot.py:16
Functionspectral_de_normalize_torch
(magnitudes)
modules/hifigan/mel_utils.py:36
Methodstep
Run one step.
modules/parallel_wavegan/optimizers/radam.py:27
Methodstore_to_file
Write vocab file to disk. Vocab files have one token per line. The file ends in a newline. Reserved tokens are written to the vocab f
utils/text_encoder.py:290
Methodsynthesis
Synthesis with PQMF. Args: x (Tensor): Input tensor (B, subbands, T // subbands). Returns: Tensor: Output te
modules/parallel_wavegan/layers/pqmf.py:118
Functiontensors_to_scalars
(metrics)
utils/__init__.py:17
Methodtest_dataloader
(self)
tasks/base_task.py:297
Methodtest_dataloader
(self)
tasks/tts/fs2.py:60
Methodtest_end
(self, outputs)
tasks/base_task.py:212
Methodtest_item_names
(self)
data_gen/singing/binarize.py:83
Methodtest_item_names
(self)
data_gen/tts/base_binarizer.py:68
Methodtest_start
(self)
tasks/base_task.py:206
Methodtest_step
(self, sample, batch_idx)
tasks/base_task.py:209
Methodtest_step
(self, sample, batch_idx)
tasks/tts/fs2.py:340
Methodtoken_gen
()
utils/text_encoder.py:239
Methodtrain_dataloader
(self)
tasks/base_task.py:293
Methodtrain_dataloader
(self)
tasks/tts/fs2.py:49
Methodtrain_item_names
(self)
data_gen/singing/binarize.py:75
Methodtrain_item_names
(self)
data_gen/tts/base_binarizer.py:60
Methodtraining_tqdm_dict
(self)
utils/pl_utils.py:589
Methodunk
(self)
utils/text_encoder.py:284
Functionunpack_dict_to_list
(samples)
utils/__init__.py:164
Methodval_dataloader
(self)
tasks/base_task.py:301
Methodval_dataloader
(self)
tasks/tts/fs2.py:55
Methodvalid_item_names
(self)
data_gen/singing/binarize.py:79
Methodvalid_item_names
(self)
data_gen/tts/base_binarizer.py:64
Methodvalidation_step
(self, sample, batch_idx)
usr/diffsinger_task.py:49
Methodvalidation_step
(self, sample, batch_idx)
usr/diffsinger_task.py:155
Methodvalidation_step
(self, sample, batch_idx)
usr/diffspeech_task.py:80
Methodvalidation_step
(self, sample, batch_idx)
tasks/tts/fs2.py:81
Methodvalidation_step
(self, sample, batch_idx)
tasks/tts/pe.py:117
Methodvocab_size
(self)
utils/text_encoder.py:101
Methodvocab_size
(self)
utils/text_encoder.py:146
Methodvocab_size
(self)
utils/text_encoder.py:221
Methodwav2mfcc
(wav_fn)
vocoders/pwg.py:125
Methodwav2spec
(wav_fn, **kwargs)
usr/singingvocoder/highgan.py:64
Methodwav2spec
:param wav_fn: str :return: wav, mel: [T, 80]
vocoders/base_vocoder.py:33
Functionwrite_hdf5
Write dataset to hdf5. Args: hdf5_name (str): Hdf5 dataset filename. hdf5_path (str): Dataset path in hdf5. write_data (n
modules/parallel_wavegan/utils/utils.py:66
← previous601–694 of 694, ranked by callers