MCPcopy Create free account

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

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

Method_rescale_annotations
(self, bboxes, crop_coordinates)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:551
Method_rescale_annotations
(self, bboxes, crop_coordinates)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:879
Method_rescale_annotations
(self, bboxes, crop_coordinates)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:561
Method_reset_parameters
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:186
Method_reset_parameters
(m)
NeuralSeq/modules/parallel_wavegan/models/melgan.py:422
Method_sizes
(self)
NeuralSeq/tasks/base_task.py:39
Function_stft
(y, hparams)
NeuralSeq/utils/audio.py:29
Method_training_step
(self, sample, batch_idx, _)
NeuralSeq/tasks/svs/task.py:56
Method_training_step
(self, sample, batch_idx, opt_idx)
NeuralSeq/tasks/tts/ps_flow.py:19
Method_training_step
(self, sample, batch_idx, optimizer_idx)
NeuralSeq/tasks/tts/fs2_adv.py:32
Method_training_step
(self, sample, batch_idx, _)
NeuralSeq/tasks/tts/fs2.py:73
Method_training_step
(self, sample, batch_idx, _)
NeuralSeq/tasks/tts/pe.py:111
Method_training_step
(self, sample, batch_idx, optimizer_idx)
NeuralSeq/tasks/tts/ps_adv.py:59
Method_validation_end
(self, outputs)
NeuralSeq/tasks/tts/fs2.py:96
Functionaccelerated_dtw
Computes Dynamic Time Warping (DTW) of two sequences in a faster way. Instead of iterating through each element and calculating each distance
NeuralSeq/utils/dtw.py:58
Functionadd_Poisson_noise
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:408
Methodadd_diversity
(seq_table, logprob, t, divm, diversity_lambda, bdash)
audio_to_text/captioning/models/base_model.py:358
Functionadd_model_config
add model config path or file and update registry
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/factory.py:252
Functionadd_resize
(img, sf=4)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:343
Functionadd_sharpening
USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:299
Functionadd_speckle_noise
(img, noise_level1=2, noise_level2=25)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:390
Methodafter_infer
(self, predictions, sil_start_frame=0)
NeuralSeq/tasks/tts/tts_base.py:173
Functionamp_to_db
(x)
NeuralSeq/utils/audio.py:51
Methodanalysis
Analysis with PQMF. Args: x (Tensor): Input tensor (B, 1, T). Returns: Tensor: Output tensor (B, subbands, T
NeuralSeq/modules/parallel_wavegan/layers/pqmf.py:105
Functionanalytic_kernel
Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:49
Functionanalytic_kernel
Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:49
Functionapply_weight_norm
(m)
NeuralSeq/modules/hifigan/hifigan.py:20
Methodaudio_infer
Forward one audio and produce the audio embedding Parameters ---------- audio: (audio_length) the time-domain au
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:767
Functionaugment_img_np3
(img, mode=0)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:441
Functionaugment_img_tensor
Kai Zhang (github: https://github.com/cszn)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:422
Functionaugment_img_tensor4
Kai Zhang (github: https://github.com/cszn)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:401
Functionaugment_imgs
(img_list, hflip=True, rot=True)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:469
Methodbackward
(ctx, grad_output)
mono2binaural/src/warping.py:35
Methodbackward
(ctx, grad_output)
NeuralSeq/modules/commons/common_layers.py:474
Functionbart_embeddings
(text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/bert.py:28
Functionbatch_by_size
Yield mini-batches of indices bucketed by size. Batches may contain sequences of different lengths. Args: indices (List[int]): o
NeuralSeq/utils/__init__.py:89
Functionbert_embeddings
(text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/bert.py:6
Functionbetas_for_alpha_bar
Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/util.py:77
Functionblur
x: image, NxcxHxW k: kernel, Nx1xhxw
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:128
Functionblur
x: image, NxcxHxW k: kernel, Nx1xhxw
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:128
Methodbn_eval
(module)
audio_to_text/captioning/models/encoder.py:579
Methodbn_eval
(module)
audio_to_text/captioning/models/encoder.py:668
Functionbn_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:185
Methodbuild_embedding
(self, dictionary, embed_dim)
NeuralSeq/modules/syntaspeech/syntaspeech.py:117
Methodbuild_mfa_inputs
(cls, item, mfa_input_dir, mfa_group, wav_processed_tmp, preprocess_args)
NeuralSeq/data_gen/tts/base_preprocess.py:222
Methodbuild_model
(self)
NeuralSeq/modules/GenerSpeech/task/generspeech.py:33
Methodbuild_model
(self)
NeuralSeq/inference/svs/ds_e2e.py:14
Methodbuild_model
(self)
NeuralSeq/inference/svs/ds_cascade.py:9
Methodbuild_model
(self)
NeuralSeq/inference/tts/PortaSpeech.py:13
Methodbuild_model
(self)
NeuralSeq/inference/tts/GenerSpeech.py:14
Methodbuild_model
(self)
NeuralSeq/tasks/tts/fs2_adv.py:12
Methodbuild_model
(self)
NeuralSeq/tasks/tts/fs2.py:66
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/svs/diffspeech_task.py:40
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/tts/ps.py:141
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/tts/tts_base.py:149
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/tts/tts.py:43
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/tts/ps_flow.py:113
Methodbuild_optimizer
(self, model)
NeuralSeq/tasks/tts/ps_adv.py:285
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/svs/task.py:75
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/tts/ps.py:149
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/tts/tts_base.py:143
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/tts/tts.py:40
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/tts/ps_flow.py:134
Methodbuild_scheduler
(self, optimizer)
NeuralSeq/tasks/tts/ps_adv.py:301
Methodbuild_tts_model
(self)
NeuralSeq/tasks/svs/diffsinger_task.py:40
Methodbuild_tts_model
(self)
NeuralSeq/tasks/svs/diffsinger_task.py:126
Methodbuild_tts_model
(self)
NeuralSeq/tasks/svs/diffsinger_task.py:398
Methodbuild_tts_model
(self)
NeuralSeq/tasks/svs/task.py:16
Methodbuild_tts_model
(self)
NeuralSeq/tasks/svs/diffspeech_task.py:23
Methodbuild_tts_model
(self)
NeuralSeq/tasks/tts/synta.py:12
Methodbuild_tts_model
(self)
NeuralSeq/tasks/tts/ps_flow.py:14
Methodbuild_tts_model
(self)
NeuralSeq/tasks/tts/pe.py:106
Methodbuild_tts_model
(self)
NeuralSeq/tasks/tts/ps_adv.py:29
Methodcal_clap_score
(self,txt,audio_path)
text_to_audio/Make_An_Audio/wav_evaluation/models/CLAPWrapper.py:217
Functioncalc_celoss
(pred, target)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/loss.py:286
Functioncalculate_psnr
(img1, img2, border=0)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:621
Functioncalculate_ssim
calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:642
Methodcall
Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, 1, C). Returns: Tensor: Padded tensor (
NeuralSeq/modules/parallel_wavegan/layers/tf_layers.py:25
Methodcall
Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, 1, C). Returns: Tensors: Output tensor
NeuralSeq/modules/parallel_wavegan/layers/tf_layers.py:60
Methodcall
Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, 1, C). Returns: Tensor: Output tensor (
NeuralSeq/modules/parallel_wavegan/layers/tf_layers.py:115
Functionchannel_convert
(in_c, tar_type, img_list)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:597
Methodchntext2cardinal
(self)
NeuralSeq/utils/text_norm.py:428
Methodchntext2fraction
(self)
NeuralSeq/utils/text_norm.py:494
Methodchntext2percentage
(self)
NeuralSeq/utils/text_norm.py:593
Functionchunked_worker
(worker_id, map_func, args, results_queue=None, init_ctx_func=None)
NeuralSeq/utils/multiprocess_utils.py:6
Functionclassical_degradation
blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:284
Functionclassical_degradation
blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:284
Methodclassify_audio_files_per_batch
r"""Compute classification probabilities for each audio recording in a batch and each class label
text_to_audio/Make_An_Audio/wav_evaluation/models/CLAPWrapper.py:254
Methodclassify_audio_files_per_batch
r"""Compute classification probabilities for each audio recording in a batch and each class label
text_to_audio/Make_An_Audio/ldm/modules/encoders/CLAP/CLAPWrapper.py:235
Methodclear_audio
(self)
audio-chatgpt.py:1364
Methodclear_buffer
(self, incremental_state)
NeuralSeq/modules/commons/transformer.py:129
Methodclear_buffer
(self, incremental_state=None)
NeuralSeq/modules/commons/transformer.py:478
Methodclear_buffer
(self, *args)
NeuralSeq/modules/commons/transformer.py:645
Methodclear_button
(self)
audio-chatgpt.py:1372
Methodclear_image
(self)
audio-chatgpt.py:1368
Methodclear_input_audio
(self)
audio-chatgpt.py:1366
Methodclear_video
(self)
audio-chatgpt.py:1370
Functionclip_bce
Binary crossentropy loss.
audio_detection/audio_infer/pytorch/losses.py:5
Functioncollate_1d
Convert a list of 1d tensors into a padded 2d tensor.
NeuralSeq/utils/__init__.py:44
Functioncollate_2d
Convert a list of 2d tensors into a padded 3d tensor.
NeuralSeq/utils/__init__.py:62
← previousnext →1,701–1,800 of 2,752, ranked by callers