Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/AIGC-Audio/AudioGPT
/ functions
Functions
2,752 in github.com/AIGC-Audio/AudioGPT
⨍
Functions
2,752
◇
Types & classes
604
Method
seq_forward
(self, input_dict)
audio_to_text/captioning/models/transformer_model.py:104
Method
seq_forward
(self, input_dict)
audio_to_text/captioning/models/transformer_model.py:234
Method
set_activation_status
(self, status=True)
NeuralSeq/modules/GenerSpeech/model/mixstyle.py:34
Method
set_buffer
(self, *args)
NeuralSeq/modules/commons/transformer.py:648
Method
set_ddi
(self, ddi)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:96
Method
set_ddi
(self, ddi)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:38
Method
set_index
(cls, start_idx, end_idx)
audio_to_text/captioning/models/base_model.py:41
Method
shared_step
(self, batch, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:511
Method
shared_step
(self, batch, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:863
Method
shared_step
(self, batch, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:507
Function
shave
(img_in, border=0)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:510
Function
shift_1d
(x)
NeuralSeq/modules/commons/rel_transformer.py:17
Method
show_mel_fn
(self, input_audio_path)
audio-chatgpt.py:492
Method
shuffle_batches
(batches)
NeuralSeq/tasks/tts/tts_base.py:100
Method
shuffle_batches
(batches)
NeuralSeq/tasks/tts/tts.py:57
Function
silu
(x)
NeuralSeq/modules/diff/net.py:54
Function
single2tensor3
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:302
Function
single2tensor4
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:307
Function
single2tensor5
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:329
Function
single2uint
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:254
Function
single2uint16
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:264
Function
single32tensor5
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:333
Function
single42tensor4
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:337
Function
softmax
(x, dim)
NeuralSeq/utils/__init__.py:160
Method
sp_phonemes
()
NeuralSeq/data_gen/tts/txt_processors/base_text_processor.py:19
Method
spec2wav
(self, mel, **kwargs)
NeuralSeq/vocoders/hifigan.py:55
Method
spec2wav
:param mel: [T, 80] :return: wav: [T']
NeuralSeq/vocoders/base_vocoder.py:23
Function
spec_f0_to_figure
(spec, f0s, figsize=None)
NeuralSeq/utils/plot.py:16
Function
spectral_de_normalize_torch
(magnitudes)
NeuralSeq/modules/hifigan/mel_utils.py:36
Method
speech
(self, speech_input, state)
audio-chatgpt.py:1294
Function
split_imageset
split the large images from original_dataroot into small overlapped images with size (p_size)x(p_size), and save them into taget_dataroot; on
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:125
Function
split_train_cv
split_train_cv :param data_frame: :type data_frame: pd.DataFrame :param frac: :type frac: float
audio_detection/target_sound_detection/src/utils.py:55
Function
squeeze
(x, x_mask=None, n_sqz=2)
NeuralSeq/modules/commons/normalizing_flow/utils.py:4
Function
srmd_degradation
blur + bicubic downsampling Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:240
Function
srmd_degradation
blur + bicubic downsampling Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:240
Method
state_dict
(self)
audio_detection/audio_infer/utils/data_generator.py:252
Method
state_dict
(self)
audio_detection/audio_infer/utils/data_generator.py:348
Method
step
Run one step.
NeuralSeq/modules/parallel_wavegan/optimizers/radam.py:27
Method
stochastic_encode
(self, x0, t, use_original_steps=False, noise=None)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddim.py:228
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:93
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:191
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:268
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:334
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:409
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:492
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:582
Method
store_inverse
(self)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:717
Method
store_inverse
(self)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:35
Method
store_inverse
(self)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:133
Method
store_inverse
(self)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:210
Method
store_inverse
(self)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:264
Method
store_inverse
(self)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:353
Method
store_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
NeuralSeq/utils/text_encoder.py:290
Function
store_yaml
(config, config_file)
audio_to_text/captioning/utils/train_util.py:93
Function
string_begins_with
(prefix, str)
text_to_audio/Make_An_Audio/ldm/modules/x_transformer.py:102
Function
surf
(Z, cmap='rainbow', figsize=None)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:47
Method
synthesis
Synthesis with PQMF. Args: x (Tensor): Input tensor (B, subbands, T // subbands). Returns: Tensor: Output te
NeuralSeq/modules/parallel_wavegan/layers/pqmf.py:118
Function
tensor2img
Converts a torch Tensor into an image Numpy array of BGR channel order Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:342
Function
tensor2single
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:312
Function
tensor2single3
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:320
Function
tensor2uint
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:289
Method
test_dataloader
(self)
NeuralSeq/tasks/base_task.py:298
Method
test_dataloader
(self)
NeuralSeq/tasks/tts/tts_base.py:85
Method
test_dataloader
(self)
NeuralSeq/tasks/tts/fs2.py:58
Method
test_dataloader
(self)
NeuralSeq/tasks/vocoder/vocoder_base.py:33
Method
test_end
(self, outputs)
NeuralSeq/tasks/base_task.py:213
Method
test_end
(self, outputs)
NeuralSeq/tasks/tts/tts_base.py:284
Method
test_end
(self, outputs)
NeuralSeq/tasks/vocoder/vocoder_base.py:65
Method
test_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer.py:68
Method
test_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:72
Method
test_start
(self)
NeuralSeq/tasks/base_task.py:207
Method
test_start
(self)
NeuralSeq/tasks/tts/ps.py:155
Method
test_start
(self)
NeuralSeq/tasks/tts/tts_base.py:164
Method
test_start
(self)
NeuralSeq/tasks/tts/ps_adv.py:327
Method
test_start
(self)
NeuralSeq/tasks/vocoder/vocoder_base.py:60
Method
test_step
(self, sample, batch_idx)
NeuralSeq/modules/GenerSpeech/task/generspeech.py:125
Method
test_step
(self, sample, batch_idx)
NeuralSeq/tasks/svs/diffsinger_task.py:208
Method
test_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/ps.py:161
Method
test_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/fs2.py:338
Method
test_step
(self, sample, batch_idx)
NeuralSeq/tasks/tts/ps_adv.py:333
Method
test_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:197
Method
test_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:397
Method
test_step
(self, batch, batch_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:124
Method
test_step
(self,batch,batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:516
Method
test_step
(self,batch,batch_idx)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:512
Method
token_gen
()
NeuralSeq/utils/text_encoder.py:239
Function
tokenize
Returns the tokenized representation of given input string(s) Parameters ---------- texts : Union[str, List[str]] An input s
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/tokenizer.py:152
Function
tokenize_caption
Build vocabulary from csv file with a given threshold to drop all counts < threshold Args: input_json(string): Preprossessed json file. S
audio_to_text/captioning/utils/tokenize_caption.py:7
Function
trace_model
(model, batch_size=256, device=torch.device("cpu"))
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:897
Method
train
(self, mode)
audio_to_text/captioning/models/encoder.py:665
Method
train_dataloader
(self)
NeuralSeq/tasks/base_task.py:294
Method
train_dataloader
(self)
NeuralSeq/tasks/tts/tts_base.py:56
Method
train_dataloader
(self)
NeuralSeq/tasks/tts/fs2.py:47
Method
train_dataloader
(self)
NeuralSeq/tasks/vocoder/vocoder_base.py:23
Method
train_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer.py:60
Method
train_item_names
(self)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:64
Function
train_labelencoder
encode_labels Encodes labels :param labels: pd.Series representing the raw labels e.g., Speech, Water :param encoder (optional): Encoder
audio_detection/target_sound_detection/src/utils.py:116
Method
training_step
(self, batch, batch_idx, optimizer_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:142
Method
training_step
(self, batch, batch_idx, optimizer_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:372
Method
training_step
(self, batch, batch_idx, optimizer_idx)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:89
← previous
next →
2,601–2,700 of 2,752, ranked by callers