MCPcopy Create free account

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

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

Method__init__
(self, d_out: int, text_model: str, transformer_embed_dim: int)
text_to_audio/Make_An_Audio/ldm/modules/encoders/CLAP/clap.py:43
Method__init__
(self, model_fp, device)
text_to_audio/Make_An_Audio/ldm/modules/encoders/CLAP/CLAPWrapper.py:23
Method__init__
(self, sr, nfft, fmin, fmax, nmels, hoplen, spec_power, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:16
Method__init__
(self, min_val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:41
Method__init__
(self, val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:52
Method__init__
(self, val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:63
Method__init__
(self, val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:74
Method__init__
(self, val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:85
Method__init__
(self, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:96
Method__init__
(self, min_val, max_val, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:106
Method__init__
(self, max_len, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:118
Method__init__
(self, inverse=False)
text_to_audio/Make_An_Audio/ldm/data/extract_mel_spectrogram.py:129
Method__init__
(self, embed_dim, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:285
Method__init__
(self, ddconfig, lossconfig, embed_dim, ck
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:306
Method__init__
(self, *args, vq_interface=False, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:458
Method__init__
(self, *args, vq_interface=False, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:185
Method__init__
(self, concat_keys: tuple, finetune_keys=("model.diffusion_model.input_block
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:1077
Method__init__
(self, concat_keys=("mask", "masked_image"), masked_image_key="masked_image"
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:1220
Method__init__
(self, model, schedule="linear", **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddim.py:13
Method__init__
(self, diffusion_path, num_classes, ckpt_path=None,
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:30
Method__init__
(self, first_stage_config, cond_stage_config, num_timesteps
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:424
Method__init__
(self, diff_model_config, conditioning_key)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1394
Method__init__
(self, cond_stage_key, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1425
Method__init__
(self, model, schedule="linear", **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/plms.py:12
Method__init__
(self, first_stage_config, cond_stage_config, num_timesteps
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:36
Method__init__
(self, h, channels, kernel_size=3, dilation=(1, 3))
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:63
Method__init__
(self, h)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:87
Method__init__
(self, period, kernel_size=5, stride=3, use_spectral_norm=False)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:140
Method__init__
(self)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:176
Method__init__
(self, use_spectral_norm=False)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:203
Method__init__
(self)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:231
Method__init__
(self, ckpt_vocoder,device='cuda')
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:297
Method__init__
(self, vocoder_args,device='cuda')
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:320
Method__init__
(self, h, channels, kernel_size=3, dilation=(1, 3, 5), activation=None)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:31
Method__init__
(self, h, channels, kernel_size=3, dilation=(1, 3), activation=None)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:91
Method__init__
(self, h, period, kernel_size=5, stride=3, use_spectral_norm=False)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:217
Method__init__
(self, h)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:254
Method__init__
(self, cfg, resolution)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:278
Method__init__
(self, cfg, debug=False)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:331
Method__init__
(self, ckpt_vocoder,device='cuda')
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:394
Method__init__
Initialization. INPUT: - in_features: shape of the input - alpha - trainable parameter that controls frequenc
text_to_audio/Make_An_Audio/vocoder/bigvgan/activations.py:79
Method__init__
(self, ratio=2, kernel_size=None)
text_to_audio/Make_An_Audio/vocoder/bigvgan/alias_free_torch/resample.py:37
Method__init__
(self, cutoff=0.5, half_width=0.6, stride: int = 1,
text_to_audio/Make_An_Audio/vocoder/bigvgan/alias_free_torch/filter.py:61
Method__init__
(self, activation, up_ratio: int = 2, down_ratio: int = 2,
text_to_audio/Make_An_Audio/vocoder/bigvgan/alias_free_torch/act.py:9
Method__iter__
Return the iterator of the scp file.
NeuralSeq/modules/parallel_wavegan/utils/utils.py:163
Method__iter__
(self)
NeuralSeq/utils/text_norm.py:170
Method__iter__
(self)
NeuralSeq/tasks/vocoder/dataset_utils.py:42
Method__iter__
Generate batch meta for training. Returns: batch_meta: e.g.: [ {'hdf5_path': string, 'index_in_hdf5': int},
audio_detection/audio_infer/utils/data_generator.py:130
Method__iter__
Generate batch meta for training. Returns: batch_meta: e.g.: [ {'hdf5_path': string, 'index_in_hdf5': int},
audio_detection/audio_infer/utils/data_generator.py:214
Method__iter__
Generate batch meta for training. Returns: batch_meta: e.g.: [ {'hdf5_path': string, 'index_in_hdf5': int},
audio_detection/audio_infer/utils/data_generator.py:286
Method__iter__
Generate batch meta for training. Returns: batch_meta: e.g.: [ {'hdf5_path': string, 'index_in_h
audio_detection/audio_infer/utils/data_generator.py:377
Method__len__
Return the length of the scp file.
NeuralSeq/modules/parallel_wavegan/utils/utils.py:159
Method__len__
(self)
NeuralSeq/utils/indexed_datasets.py:38
Method__len__
(self)
NeuralSeq/utils/text_encoder.py:224
Method__len__
(self)
NeuralSeq/tasks/base_task.py:48
Method__len__
(self)
NeuralSeq/tasks/vocoder/dataset_utils.py:45
Method__len__
(self)
audio_to_text/captioning/utils/build_vocab.py:31
Method__len__
(self)
audio_to_text/captioning/utils/build_vocab_ltp.py:27
Method__len__
(self)
audio_to_text/captioning/utils/build_vocab_spacy.py:27
Method__len__
(self)
text_to_audio/Make_An_Audio/ldm/modules/losses_audio/vggishish/dataset.py:66
Method__repr__
(self)
NeuralSeq/modules/GenerSpeech/model/mixstyle.py:31
Method__repr__
(self)
NeuralSeq/utils/text_norm.py:73
Method__setstate__
Set state.
NeuralSeq/modules/parallel_wavegan/optimizers/radam.py:23
Method__str__
(self)
NeuralSeq/utils/text_norm.py:90
Method__str__
(self)
NeuralSeq/utils/text_norm.py:126
Method_apply_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:186
Method_apply_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:284
Method_apply_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:418
Method_apply_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:172
Method_apply_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:408
Function_conv_filter
convert patch embedding weight from manual patchify + linear proj to conv
audio_detection/audio_infer/pytorch/models.py:943
Function_convert_to_rgb
(image)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/transform.py:5
Function_convert_weights_to_fp16
(l)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:825
Function_f
(cls)
NeuralSeq/data_gen/tts/txt_processors/base_text_processor.py:6
Function_f
(cls)
NeuralSeq/data_gen/tts/wav_processors/base_processor.py:5
Method_forward
(self, x, context=None)
text_to_audio/Make_An_Audio/ldm/modules/attention.py:211
Method_forward
(self, x, emb)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:255
Method_forward
(self, x)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:318
Function_get_data_loader
(self)
NeuralSeq/utils/pl_utils.py:57
Method_init_weights
(self, m)
audio_detection/audio_infer/pytorch/models.py:634
Method_init_weights
(self, m)
audio_detection/audio_infer/pytorch/models.py:690
Method_init_weights
(self, m)
audio_detection/audio_infer/pytorch/models.py:768
Method_init_weights
(self, m)
audio_detection/audio_infer/pytorch/models.py:808
Method_init_weights
(self, m)
audio_detection/audio_infer/pytorch/models.py:871
Method_init_weights
(self, m)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:756
Function_inner_uniform
(tensor)
sound_extraction/model/modules.py:454
Function_istft
(y, hparams)
NeuralSeq/utils/audio.py:34
Function_load_old_metrics
(workspace, filename, iteration, data_type)
audio_detection/audio_infer/utils/plot_statistics.py:1490
Method_predict_eps_from_xstart
(self, x_t, t, pred_xstart)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:664
Method_predict_eps_from_xstart
(self, x_t, t, pred_xstart)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:992
Method_predict_eps_from_xstart
(self, x_t, t, pred_xstart)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:682
Method_prior_bpd
Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:668
Method_prior_bpd
Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:996
Method_prior_bpd
Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:686
Method_remove_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:175
Method_remove_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:293
Method_remove_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:427
Method_remove_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:161
Method_remove_weight_norm
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:397
Method_repeat_one_sequence
Repeat each frame according to duration.
NeuralSeq/modules/syntaspeech/syntactic_graph_encoder.py:92
← previousnext →1,601–1,700 of 2,752, ranked by callers