MCPcopy Create free account

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

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

⨍ Functions 2,752◇ Types & classes 604
↓ 1 callersFunctionplot_classwise_iteration_map
(args)
audio_detection/audio_infer/utils/plot_for_paper.py:52
↓ 1 callersFunctionplot_complexity_map
(args)
audio_detection/audio_infer/utils/plot_for_paper.py:298
↓ 1 callersFunctionplot_flops
(args)
audio_detection/audio_infer/utils/plot_statistics.py:1852
↓ 1 callersFunctionplot_for_paper
(args)
audio_detection/audio_infer/utils/plot_statistics.py:705
↓ 1 callersFunctionplot_for_paper2
(args)
audio_detection/audio_infer/utils/plot_statistics.py:965
↓ 1 callersFunctionplot_long_fig
(args)
audio_detection/audio_infer/utils/plot_statistics.py:1782
↓ 1 callersFunctionplot_long_fig
(args)
audio_detection/audio_infer/utils/plot_for_paper.py:345
↓ 1 callersMethodplot_pitch
(self, batch_idx, model_out, sample)
NeuralSeq/tasks/tts/pe.py:139
↓ 1 callersFunctionplot_six_figures
(args)
audio_detection/audio_infer/utils/plot_for_paper.py:92
↓ 1 callersMethodpostprocess
(cls, txt_struct, preprocess_args)
NeuralSeq/data_gen/tts/txt_processors/base_text_processor.py:27
↓ 1 callersMethodpostprocess_output
(self, output)
NeuralSeq/inference/svs/base_svs_infer.py:225
↓ 1 callersMethodpostprocess_output
(self, output)
NeuralSeq/inference/tts/base_tts_infer.py:63
↓ 1 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
NeuralSeq/modules/diff/diffusion.py:239
↓ 1 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
NeuralSeq/modules/diff/shallow_diffusion_tts.py:134
↓ 1 callersMethodprepare_beamsearch_decoder_input
(self, input_dict, output_i)
audio_to_text/captioning/models/base_model.py:338
↓ 1 callersMethodprepare_beamsearch_output
(self, input_dict)
audio_to_text/captioning/models/base_model.py:320
↓ 1 callersMethodprepare_dbs_decoder_input
(self, input_dict, output_i)
audio_to_text/captioning/models/base_model.py:466
↓ 1 callersMethodprepare_decoder_input
Prepare the inp ut dict for the decoder
audio_to_text/captioning/models/base_model.py:194
↓ 1 callersFunctionprepare_plot_long_4_rows
(sorted_lbs)
audio_detection/audio_infer/utils/plot_statistics.py:1679
↓ 1 callersFunctionprepare_plot_long_4_rows
(sorted_lbs)
audio_detection/audio_infer/utils/plot_for_paper.py:436
↓ 1 callersMethodpreprocess_audio
r"""Load list of audio files and return raw audio
text_to_audio/Make_An_Audio/wav_evaluation/models/CLAPWrapper.py:151
↓ 1 callersMethodpreprocess_audio
r"""Load list of audio files and return raw audio
text_to_audio/Make_An_Audio/ldm/modules/encoders/CLAP/CLAPWrapper.py:145
↓ 1 callersMethodpreprocess_input
:param inp: {'text': str, 'item_name': (str, optional), 'spk_name': (str, optional)} :return:
NeuralSeq/inference/svs/base_svs_infer.py:155
↓ 1 callersMethodpreprocess_input
(self, inp)
NeuralSeq/inference/tts/base_tts_infer.py:57
↓ 1 callersMethodpreprocess_phoneme_level_input
(self, inp)
NeuralSeq/inference/svs/base_svs_infer.py:141
↓ 1 callersMethodpreprocess_text
(text)
NeuralSeq/data_gen/tts/txt_processors/zh.py:15
↓ 1 callersMethodpreprocess_text
r"""Load list of class labels and return tokenized text
text_to_audio/Make_An_Audio/wav_evaluation/models/CLAPWrapper.py:166
↓ 1 callersMethodpreprocess_text
r"""Load list of class labels and return tokenized text
text_to_audio/Make_An_Audio/ldm/modules/encoders/CLAP/CLAPWrapper.py:155
↓ 1 callersMethodpreprocess_word_level_input
(self, inp)
NeuralSeq/inference/svs/base_svs_infer.py:72
↓ 1 callersMethodprint_nan_gradients
(self)
NeuralSeq/utils/pl_utils.py:1079
↓ 1 callersFunctionprint_results
(args)
audio_detection/audio_infer/utils/plot_statistics.py:1924
↓ 1 callersMethodprocess
(self)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:149
↓ 1 callersMethodprocess
(cls, txt, pre_align_args)
NeuralSeq/data_gen/tts/txt_processors/zh_g2pM.py:23
↓ 1 callersFunctionprocess_utterance
(wav_path, fft_size=1024, hop_size=256, win_
NeuralSeq/data_gen/tts/data_gen_utils.py:93
↓ 1 callersMethodprocess_wav
(item_name, wav_fn, processed_dir, wav_processed_tmp, preprocess_args)
NeuralSeq/data_gen/tts/base_preprocess.py:157
↓ 1 callersMethodprogressive_denoising
(self, cond, shape, verbose=True, callback=None, quantize_denoised=False, img_ca
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:780
↓ 1 callersMethodprogressive_denoising
(self, cond, shape, verbose=True, callback=None, quantize_denoised=False, img_ca
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1108
↓ 1 callersMethodprogressive_denoising
(self, cond, shape, verbose=True, callback=None, quantize_denoised=False, img_ca
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:798
↓ 1 callersMethodprune
Prune the shape of x after transpose convolution.
sound_extraction/model/modules.py:151
↓ 1 callersMethodprune
Prune the shape of x after transpose convolution.
sound_extraction/model/modules.py:201
↓ 1 callersMethodprune
Prune the shape of x after transpose convolution.
sound_extraction/model/modules.py:254
↓ 1 callersMethodprune
Prune the shape of x after transpose convolution.
sound_extraction/model/modules.py:309
↓ 1 callersMethodq_posterior
(self, x_start, x_t, t)
NeuralSeq/modules/diff/diffusion.py:245
↓ 1 callersMethodq_posterior
(self, x_start, x_t, t)
NeuralSeq/modules/diff/shallow_diffusion_tts.py:140
↓ 1 callersMethodq_sample
(self, x_start, t, noise=None)
NeuralSeq/modules/diff/diffusion.py:273
↓ 1 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:431
↓ 1 callersFunctionread_black_list
Read audio names from black list.
audio_detection/audio_infer/utils/data_generator.py:10
↓ 1 callersFunctionread_config_as_args
(config_path,args=None,is_config_str=False)
text_to_audio/Make_An_Audio/wav_evaluation/models/utils.py:5
↓ 1 callersFunctionread_metadata
Read metadata of AudioSet from a csv file. Args: csv_path: str Returns: meta_dict: {'audio_name': (audios_num,), 'target': (audi
audio_detection/audio_infer/utils/utilities.py:59
↓ 1 callersMethodremove_weight_norm
(self)
NeuralSeq/modules/hifigan/hifigan.py:63
↓ 1 callersMethodremove_weight_norm
(m)
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:354
↓ 1 callersMethodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:55
↓ 1 callersMethodreset
(self)
NeuralSeq/utils/__init__.py:33
↓ 1 callersMethodreset_noise_accs
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:202
↓ 1 callersMethodreset_parameters
Reset parameters. This initialization follows official implementation manner. https://github.com/descriptinc/melgan-neurips/blob/mast
NeuralSeq/modules/parallel_wavegan/models/melgan.py:179
↓ 1 callersMethodreset_parameters
Reset parameters. This initialization follows official implementation manner. https://github.com/descriptinc/melgan-neurips/blob/mast
NeuralSeq/modules/parallel_wavegan/models/melgan.py:415
↓ 1 callersMethodreset_parameters
(self)
NeuralSeq/modules/commons/transformer.py:190
↓ 1 callersMethodreset_parameters
(self)
NeuralSeq/modules/commons/common_layers.py:218
↓ 1 callersMethodreset_parameters
(self)
text_to_audio/Make_An_Audio/ldm/modules/losses_audio/vggishish/model.py:56
↓ 1 callersMethodresolve_root_node_address
(self, root_node)
NeuralSeq/utils/pl_utils.py:905
↓ 1 callersMethodrestore_state_if_checkpoint_exists
(self, model)
NeuralSeq/utils/pl_utils.py:628
↓ 1 callersMethodrestore_training_state
Restore trainer state. Model will get its change to update :param checkpoint: :return:
NeuralSeq/utils/pl_utils.py:683
↓ 1 callersMethodrestore_weights
To restore weights we have two cases. First, attempt to restore hpc weights. If successful, don't restore other weights.
NeuralSeq/utils/pl_utils.py:599
↓ 1 callersMethodreverse
(self, output)
text_to_audio/Make_An_Audio/ldm/modules/discriminator/model.py:66
↓ 1 callersFunctionrnnoise
(filename, out_fn=None, verbose=False, out_sample_rate=22050)
NeuralSeq/utils/audio.py:60
↓ 1 callersMethodrun_decoder
(self, x, tgt_nonpadding, ret, infer, tgt_mels=None, global_step=0, mel2word=None, ph2word
NeuralSeq/modules/syntaspeech/syntaspeech.py:211
↓ 1 callersMethodrun_model
(self, model, sample, return_output=False)
NeuralSeq/modules/GenerSpeech/task/generspeech.py:40
↓ 1 callersMethodrun_model
(self, model, sample, return_output=False, infer=False)
NeuralSeq/tasks/svs/diffsinger_task.py:140
↓ 1 callersMethodrun_model
(self, model, sample, return_output=False)
NeuralSeq/tasks/svs/diffsinger_task.py:404
↓ 1 callersMethodrun_model
(self, model, sample, return_output=False, infer=False)
NeuralSeq/tasks/svs/diffspeech_task.py:48
↓ 1 callersMethodrun_model
(self, sample, infer=False, *args, **kwargs)
NeuralSeq/tasks/tts/ps_flow.py:32
↓ 1 callersMethodrun_post_glow
(self, tgt_mels, infer, is_training, ret)
NeuralSeq/modules/GenerSpeech/model/generspeech.py:233
↓ 1 callersFunctionrun_task
()
NeuralSeq/tasks/run.py:5
↓ 1 callersMethodrun_text_encoder
(self, txt_tokens, word_tokens, ph2word, word_len, mel2word, mel2ph, style_embed, ret, graph_lst, etypes_lst,
NeuralSeq/modules/syntaspeech/syntaspeech.py:149
↓ 1 callersMethodrun_training_batch
(self, batch, batch_idx)
NeuralSeq/utils/pl_utils.py:1436
↓ 1 callersMethodrun_training_epoch
(self)
NeuralSeq/utils/pl_utils.py:1371
↓ 1 callersMethodsample
(self, cond, batch_size=16, return_intermediates=False, x_T=None, verbose=True, timesteps=None,
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1215
↓ 1 callersMethodsample_next_word
Sample the next word, given probs output by the decoder
audio_to_text/captioning/models/base_model.py:210
↓ 1 callersFunctionsave_to_dict
(s, o_={})
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:239
↓ 1 callersMethodsave_valid_result
(self, sample, batch_idx, model_out)
NeuralSeq/tasks/tts/ps_adv.py:213
↓ 1 callersFunctionsave_wav
(wav, path)
sound_extraction/utils/wav_io.py:21
↓ 1 callersMethodschedule
(self, n, **kwargs)
text_to_audio/Make_An_Audio/ldm/lr_scheduler.py:17
↓ 1 callersMethodschedule
(self, n, **kwargs)
text_to_audio/Make_An_Audio/ldm/lr_scheduler.py:59
↓ 1 callersFunctionselect_attn
:param attn_logits: [n_layers, B, n_head, T_sp, T_txt] :return:
NeuralSeq/utils/tts_utils.py:146
↓ 1 callersMethodselect_best_audio
(self, prompt, wav_list)
audio-chatgpt.py:185
↓ 1 callersMethodselect_topk_embeddings
(self, scores, embeddings, k)
audio_detection/target_sound_detection/src/models.py:1159
↓ 1 callersMethodseq_forward
(self, input_dict)
audio_to_text/captioning/models/base_model.py:135
↓ 1 callersMethodset_buffer
(self, name, tensor, incremental_state)
NeuralSeq/modules/commons/transformer.py:612
↓ 1 callersMethodset_distributed_mode
(self, distributed_backend)
NeuralSeq/utils/pl_utils.py:823
↓ 1 callersMethodsil_phonemes
(self)
NeuralSeq/utils/text_encoder.py:303
↓ 1 callersFunctionsinc
Implementation of sinc, i.e. sin(pi * x) / (pi * x) __Warning__: Different to julius.sinc, the input is multiplied by `pi`!
text_to_audio/Make_An_Audio/vocoder/bigvgan/alias_free_torch/filter.py:15
↓ 1 callersFunctionsoftmax
(x, dim)
NeuralSeq/utils/tts_utils.py:21
↓ 1 callersFunctionsort_pack_padded_sequence
(input, lengths)
audio_to_text/captioning/models/utils.py:10
↓ 1 callersFunctionsound_event_detection
Inference sound event detection result of an audio clip.
audio_detection/audio_infer/pytorch/inference.py:80
↓ 1 callersMethodsp_phonemes
()
NeuralSeq/data_gen/tts/txt_processors/zh_g2pM.py:19
↓ 1 callersFunctionspatial_average
(x, keepdim=True)
text_to_audio/Make_An_Audio/ldm/modules/losses_audio/lpaps.py:142
↓ 1 callersFunctionspearman
(args)
audio_detection/audio_infer/utils/plot_statistics.py:1900
↓ 1 callersFunctionspectral_normalize_torch
(magnitudes)
NeuralSeq/modules/hifigan/mel_utils.py:31
↓ 1 callersMethodspectrogram
(self, x)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:319
↓ 1 callersFunctionsplit_unbalanced_csv_to_partial_csvs
Split unbalanced csv to part csvs. Each part csv contains up to 50000 ids.
audio_detection/audio_infer/utils/dataset.py:17
← previousnext →1,001–1,100 of 2,752, ranked by callers