MCPcopy Create free account

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

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

Methodinput_to_batch
(self, item)
NeuralSeq/inference/tts/base_tts_infer.py:60
Functioninverse_transform_labels
(encoder, pred)
audio_detection/target_sound_detection/src/utils.py:222
Functionis_loaded
()
NeuralSeq/data_gen/tts/emotion/inference.py:39
Functionlecun_normal_
(tensor)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:246
Functionlibrosa_pad_lr
compute right padding (final frame) or both sides padding (first and final frames)
NeuralSeq/utils/audio.py:38
Functionlinear_beta_schedule
linear schedule
NeuralSeq/modules/diff/shallow_diffusion_tts.py:44
Functionlinear_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:175
Functionlist_pretrained
returns list of pretrained models Returns a tuple (model_name, pretrain_tag) by default or 'name:tag' if as_str == True
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/pretrained.py:78
Functionlist_pretrained_model_tags
return all pretrain tags for the specified model architecture
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/pretrained.py:94
FunctionloadWAV
(filename, max_frames, evalmode=True, num_eval=10)
NeuralSeq/data_gen/tts/emotion/test_emotion.py:55
Functionload_checkpoint
Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,
audio_detection/target_sound_detection/src/models.py:61
Functionload_class_label
(path)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:328
Functionload_data_binarizer
()
NeuralSeq/tasks/tts/tts_utils.py:47
Functionload_dict_from_csv
(csv, cols)
audio_to_text/captioning/utils/train_util.py:15
Functionload_model
Loads the model in memory. If this function is not explicitely called, it will be run on the first call to embed_frames() with the default w
NeuralSeq/data_gen/tts/emotion/inference.py:15
Functionload_pretrained_model
(model: torch.nn.Module, pretrained: Union[str, Dict], out
audio_to_text/captioning/utils/train_util.py:130
Methodload_size
()
NeuralSeq/tasks/tts/dataset_utils.py:28
Methodload_state_dict
(self, state)
audio_detection/audio_infer/utils/data_generator.py:259
Methodload_state_dict
(self, state)
audio_detection/audio_infer/utils/data_generator.py:354
Functionload_wav
(full_path)
NeuralSeq/modules/hifigan/mel_utils.py:10
Functionload_wav
(wav_file, sr)
NeuralSeq/utils/cwt.py:7
Methodlock
lock modules Args: unlocked_groups (int): leave last n layer groups unlocked (default: 0)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/timm_model.py:71
Methodlock
(self, unlocked_groups=0, freeze_bn_stats=False)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:214
Methodlock
(self, unlocked_groups=0, freeze_bn_stats=False)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:339
Methodlog_images
(self, batch, only_inputs=False, plot_ema=False, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:253
Methodlog_images
(self, batch, only_inputs=False,save_dir = 'mel_result_ae13_26_debug/fake_class', **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:432
Methodlog_images
(self, batch, only_inputs=False, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:159
Methodlog_images
(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None, qua
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:1133
Methodlog_images
(self, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:1258
Methodlog_images
(self, batch, N=8, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:238
Methodlog_images
(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None, qua
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1249
Methodlog_images
(self, batch, N=8, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1429
Methodlog_images
(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None, qua
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:937
Functionlp_gather_features
( pred, target, world_size=1, use_horovod=False )
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/loss.py:223
Functionmain
(output_file, eval_caption_file, eval_embedding_file, output, zh=False)
audio_to_text/captioning/utils/model_eval_diff.py:58
Functionmain
(vocab_file: str, output: str, server_hostname: str)
audio_to_text/captioning/utils/bert/create_word_embedding.py:15
Functionmake_non_pad_mask
Make mask tensor containing indices of non-padded part. Args: lengths (LongTensor or List): Batch of lengths (B,). xs (Tensor, opt
NeuralSeq/utils/tts_utils.py:270
Functionmake_positions
Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored.
NeuralSeq/utils/__init__.py:145
Methodmake_stop_target
(self, target)
NeuralSeq/tasks/tts/tts_base.py:300
Functionmax_neg_value
(t)
text_to_audio/Make_An_Audio/ldm/modules/attention.py:25
Methodmax_positions
Maximum number of supported positions.
NeuralSeq/modules/commons/transformer.py:70
Methodmax_positions
Maximum number of supported positions.
NeuralSeq/modules/commons/common_layers.py:144
Functionmean_flat
https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/nn.py#L86 Take the mean over all no
text_to_audio/Make_An_Audio/ldm/util.py:96
Methodmel_denorm
(x)
NeuralSeq/modules/fastspeech/fs2.py:243
Methodmel_norm
(x)
NeuralSeq/modules/fastspeech/fs2.py:239
Functionmel_spectrogram
(y, hparams, center=False, complex=False)
NeuralSeq/modules/hifigan/mel_utils.py:45
Methodmeta_csv_filename
(self)
NeuralSeq/data_gen/tts/base_preprocess.py:249
Methodmeta_data
(self)
NeuralSeq/configs/tts/emotion/pre_align.py:9
Methodmeta_data
(self)
NeuralSeq/configs/tts/libritts/pre_align.py:8
Methodmeta_data
(self)
NeuralSeq/egs/datasets/audio/vctk/pre_align.py:8
Methodmeta_data
(self)
NeuralSeq/egs/datasets/audio/emotion/pre_align.py:9
Methodmeta_data
(self)
NeuralSeq/egs/datasets/audio/lj/preprocess.py:5
Methodmeta_data
(self)
NeuralSeq/egs/datasets/audio/libritts/pre_align.py:8
Functionmkdir_and_rename
(path)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:166
Functionmkdirs
(paths)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:158
Functionmodcrop
(img_in, scale)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:494
Functionmodcrop_np
Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:29
Functionmodcrop_np
Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:29
Methodmode
(self)
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:9
Methodmode
(self)
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:61
Functionmove_file
(from_file, to_file)
NeuralSeq/utils/os_utils.py:10
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/base_processor.py:18
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:14
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:29
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:48
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:62
Methodname
(self)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:79
Methodnll
(self, sample, dims=[1,2,3])
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:53
Methodno_weight_decay
(self)
audio_detection/audio_infer/pytorch/models.py:895
Methodno_weight_decay
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:766
Methodno_weight_decay_keywords
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:770
Functionnormalize
(S, hparams)
NeuralSeq/utils/audio.py:55
Functionnormalize_cwt_lf0
(f0, mean, std)
NeuralSeq/utils/cwt.py:80
Functionnormalize_energy
:param audio: 1d waveform, [batchsize, *], :param alpha: the value of output range from: [-alpha,alpha] :return: 1d waveform which value
sound_extraction/utils/create_mixtures.py:45
Functionnsw_test
()
NeuralSeq/utils/text_norm.py:718
Methodnum_gpus
(self)
NeuralSeq/utils/pl_utils.py:458
Methodnum_reserved_ids
(self)
NeuralSeq/utils/text_encoder.py:43
Functionnum_to_groups
(num, divisor)
NeuralSeq/modules/diff/diffusion.py:35
Methodnum_tokens
(self, index)
NeuralSeq/tasks/base_task.py:51
Methodnum_trainable_parameters
:return: the number of trainable parameters in the model
mono2binaural/src/utils.py:66
Methodnum_workers
(self)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:346
Methodnum_workers
(self)
NeuralSeq/tasks/base_task.py:73
Methodon_after_optimization
(self, epoch, batch_idx, optimizer, optimizer_idx)
NeuralSeq/tasks/tts/fs2_adv.py:125
Methodon_after_optimization
(self, epoch, batch_idx, optimizer, optimizer_idx)
NeuralSeq/tasks/tts/ps_adv.py:319
Methodon_before_optimization
(self, opt_idx)
NeuralSeq/tasks/tts/fs2_adv.py:119
Methodon_before_optimization
(self, opt_idx)
NeuralSeq/tasks/tts/ps_adv.py:308
Methodon_before_zero_grad
(self, optimizer)
NeuralSeq/tasks/base_task.py:332
Methodon_epoch_end
(self)
NeuralSeq/tasks/base_task.py:163
Methodon_load_checkpoint
(self, checkpoint)
NeuralSeq/tasks/base_task.py:305
Methodon_train_batch_end
(self, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:92
Methodon_train_batch_end
(self, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:364
Methodon_train_batch_start
(self, batch, batch_idx, dataloader_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:93
Methodon_train_batch_start
(self, batch, batch_idx, dataloader_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:476
Methodon_train_batch_start
(self, batch, batch_idx, dataloader_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:97
Methodon_train_epoch_start
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:157
Methodon_train_start
(self)
NeuralSeq/tasks/tts/ps.py:29
Methodon_train_start
(self)
NeuralSeq/tasks/tts/ps_adv.py:51
Methodon_validation_start
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:206
Methodoptimizer_closure
()
NeuralSeq/utils/pl_utils.py:1476
Methodoptimizer_step
(self, epoch, batch_idx, optimizer, optimizer_idx)
NeuralSeq/tasks/svs/task.py:78
← previousnext →2,401–2,500 of 2,752, ranked by callers