MCPcopy Create free account

hub / github.com/AIGC-Audio/AudioGPT / functions

Functions2,752 in github.com/AIGC-Audio/AudioGPT

Methodtraining_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:198
Methodtraining_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:340
Methodtraining_tqdm_dict
(self)
NeuralSeq/utils/pl_utils.py:589
Functionuint162single
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:259
Functionuint2single
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:249
Functionuint2tensor3
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:282
Functionuint2tensor4
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:275
Functionuniform_on_device
(r1, r2, shape, device)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:39
Functionunify_energy
(*args)
sound_extraction/utils/create_mixtures.py:64
Functionuniq
(arr)
text_to_audio/Make_An_Audio/ldm/modules/attention.py:15
Methodunk
(self)
NeuralSeq/utils/text_encoder.py:284
Functionunpack_dict_to_list
(samples)
NeuralSeq/utils/__init__.py:164
Functionunsqueeze
(x, x_mask=None, n_sqz=2)
NeuralSeq/modules/commons/normalizing_flow/utils.py:19
Methodupdate_parameters
(self, model)
audio_to_text/captioning/utils/train_util.py:160
Functionupgrade_resolution
(arr, scale)
audio_detection/target_sound_detection/src/utils.py:343
Methodval_dataloader
(self)
NeuralSeq/tasks/base_task.py:302
Methodval_dataloader
(self)
NeuralSeq/tasks/tts/tts_base.py:80
Methodval_dataloader
(self)
NeuralSeq/tasks/tts/fs2.py:53
Methodval_dataloader
(self)
NeuralSeq/tasks/vocoder/vocoder_base.py:28
Methodvalid_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer.py:64
Methodvalid_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:68
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/modules/GenerSpeech/task/generspeech.py:72
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffsinger_task.py:66
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffsinger_task.py:172
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffsinger_task.py:316
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffsinger_task.py:475
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/task.py:63
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffspeech_task.py:80
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/ps.py:101
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/ps_flow.py:94
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/fs2.py:79
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/pe.py:117
Methodvalidation_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/ps_adv.py:192
Methodvalidation_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:164
Methodvalidation_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:393
Methodvalidation_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:110
Methodvalidation_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:210
Methodvalidation_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:356
Methodvocab_size
(self)
NeuralSeq/utils/text_encoder.py:101
Methodvocab_size
(self)
NeuralSeq/utils/text_encoder.py:146
Methodvocab_size
(self)
NeuralSeq/utils/text_encoder.py:221
Methodvocode
(self, spec, global_step=None)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:312
Methodvocode
(self, spec, global_step=None)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:327
Methodwav2mfcc
(wav_fn)
NeuralSeq/vocoders/pwg.py:125
Methodwav2spec
:param wav_fn: str :return: wav, mel: [T, 80]
NeuralSeq/vocoders/base_vocoder.py:33
Methodwav_processed_dirname
(self)
NeuralSeq/data_gen/tts/base_preprocess.py:253
Functionwav_to_mel_spectrogram
Derives a mel spectrogram ready to be used by the encoder from a preprocessed audio waveform. Note: this not a log-mel spectrogram.
NeuralSeq/data_gen/tts/emotion/audio.py:43
Functionweights_init
(m)
text_to_audio/Make_An_Audio/ldm/modules/discriminator/model.py:89
Methodweights_nonzero_speech
(self, target)
NeuralSeq/tasks/tts/tts_base.py:294
Methodword_forward
word encoding in, word encoding out.
NeuralSeq/modules/syntaspeech/syntactic_graph_encoder.py:103
Functionwrite_hdf5
Write dataset to hdf5. Args: hdf5_name (str): Hdf5 dataset filename. hdf5_path (str): Dataset path in hdf5. write_data (n
NeuralSeq/modules/parallel_wavegan/utils/utils.py:66
Functionycbcr2rgb
same as matlab ycbcr2rgb Input: uint8, [0, 255] float, [0, 1]
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:553
← previous2,701–2,752 of 2,752, ranked by callers