MCPcopy Create free account

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

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

Methodout2mel
(self, x)
NeuralSeq/modules/diff/diffusion.py:333
Methodout2mel
(self, x)
NeuralSeq/modules/diff/shallow_diffusion_tts.py:288
Methodoverride
(self, attrs)
NeuralSeq/modules/diff/net.py:21
Functionpad_framewise_output
Pad framewise_output to the same length as input frames. The pad value is the same as the value of the last frame. Args: framewise_out
audio_detection/audio_infer/pytorch/pytorch_utils.py:120
Functionpad_framewise_output
Pad framewise_output to the same length as input frames. The pad value is the same as the value of the last frame. Args: framewise_outpu
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:207
Methodpad_word_encoding_to_phoneme
(self, word_encoding, ph2word, t_p)
NeuralSeq/modules/syntaspeech/syntactic_graph_encoder.py:61
Functionparse
(x)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:31
Functionparse_config_or_kwargs
(config_file, **kwargs)
audio_to_text/captioning/utils/train_util.py:86
Functionparse_config_or_kwargs
parse_config_or_kwargs :param config_file: Config file that has parameters, yaml format :param **kwargs: Other alternative parameters or overw
audio_detection/target_sound_detection/src/utils.py:23
Functionparse_dataset_configs
()
NeuralSeq/tasks/tts/tts_utils.py:9
Functionparse_mel_losses
()
NeuralSeq/tasks/tts/tts_utils.py:21
Functionparse_poolingfunction
parse_poolingfunction A heler function to parse any temporal pooling Pooling is done on dimension 1 :param poolingfunction_name: :para
audio_to_text/captioning/models/encoder.py:133
Functionparse_poolingfunction
parse_poolingfunction A heler function to parse any temporal pooling Pooling is done on dimension 1 :param poolingfunction_name: :par
audio_detection/target_sound_detection/src/models.py:673
Methodph_encoding_to_word_encoding
ph_encoding: [batch, t_p, hid] ph2word: tensor [batch, t_w] word_len: tensor [batch]
NeuralSeq/modules/syntaspeech/syntactic_graph_encoder.py:48
Functionpick_and_pop
(keys, d)
text_to_audio/Make_An_Audio/ldm/modules/x_transformer.py:88
Functionplot_embedding_as_heatmap
(embed, ax=None, title="", shape=None, color_range=(0, 0.30))
NeuralSeq/data_gen/tts/emotion/inference.py:162
Methodplot_mel
(self, batch_idx, spec, spec_out, name=None)
NeuralSeq/tasks/tts/tts_base.py:157
Functionpooling1d_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:205
Functionpooling2d_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:193
Methodpostprocess_output
(self, output)
NeuralSeq/inference/tts/PortaSpeech.py:81
Functionpprint_dict
pprint_dict :param outputfun: function to use, defaults to sys.stdout :param in_dict: dict to print
audio_to_text/captioning/utils/train_util.py:43
Functionpprint_dict
pprint_dict :param outputfun: function to use, defaults to sys.stdout :param in_dict: dict to print
audio_detection/target_sound_detection/src/utils.py:95
Functionpredictions_to_time
(df, ratio)
audio_detection/target_sound_detection/src/utils.py:338
Methodprepare_beamsearch_decoder_input
(self, input_dict, output_i)
audio_to_text/captioning/models/transformer_model.py:138
Methodprepare_beamsearch_decoder_input
(self, input_dict, output_i)
audio_to_text/captioning/models/transformer_model.py:212
Methodprepare_beamsearch_decoder_input
(self, input_dict, output_i)
audio_to_text/captioning/models/transformer_model.py:255
Methodprepare_decoder_input
(self, input_dict, output)
audio_to_text/captioning/models/transformer_model.py:115
Methodprepare_decoder_input
(self, input_dict, output)
audio_to_text/captioning/models/transformer_model.py:207
Methodprepare_decoder_input
(self, input_dict, output)
audio_to_text/captioning/models/transformer_model.py:250
Methodpreprocess_first_pass
(cls, item_name, txt_raw, txt_processor, wav_fn, wav_processed_dir, wav_processe
NeuralSeq/data_gen/tts/base_preprocess.py:117
Methodpreprocess_input
:param inp: {'text': str, 'item_name': (str, optional), 'spk_name': (str, optional)} :return:
NeuralSeq/inference/tts/PortaSpeech.py:37
Methodpreprocess_input
:param inp: {'text': str, 'item_name': (str, optional), 'spk_name': (str, optional)} :return:
NeuralSeq/inference/tts/GenerSpeech.py:20
Methodpreprocess_second_pass
(cls, word, ph, spk_name, word_encoder, ph_encoder, spk_map)
NeuralSeq/data_gen/tts/base_preprocess.py:208
Functionprint_arch
(model, model_name='model')
NeuralSeq/utils/__init__.py:240
Functionprocess
(input_json: str, output_file: str, threshold: int = 1, keep_punctuation:
audio_to_text/captioning/utils/build_vocab.py:134
Functionprocess
(input_json: str, output_file: str, output_json: str = None, threshold: in
audio_to_text/captioning/utils/build_vocab_ltp.py:131
Functionprocess
(input_json: str, output_file: str, output_json: str = None, threshold: in
audio_to_text/captioning/utils/build_vocab_spacy.py:130
Methodprocess
(cls, txt, preprocess_args)
NeuralSeq/data_gen/tts/txt_processors/en.py:66
Methodprocess
(cls, txt, preprocess_args)
NeuralSeq/data_gen/tts/txt_processors/base_text_processor.py:23
Methodprocess
(cls, txt, pre_align_args)
NeuralSeq/data_gen/tts/txt_processors/zh.py:28
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/base_processor.py:24
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:17
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:32
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:51
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:65
Methodprocess
(self, input_fn, sr, tmp_dir, processed_dir, item_name, preprocess_args)
NeuralSeq/data_gen/tts/wav_processors/common_processors.py:82
Functionprocess_ipc
(index_path, classes_num, filename)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:225
Methodprocess_item
(cls, item_name, ph, txt, tg_fn, wav_fn, spk_id, emotion, encoder, binarization_args)
NeuralSeq/data_gen/tts/base_binarizer_emotion.py:215
Methodprune
Prune the shape of x after transpose convolution.
sound_extraction/model/modules.py:94
Methodq_mean_variance
(self, x_start, t)
NeuralSeq/modules/diff/diffusion.py:233
Methodq_mean_variance
(self, x_start, t)
NeuralSeq/modules/diff/shallow_diffusion_tts.py:128
Methodquantize
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:195
Functionread_img
(path)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:220
Methodreceptive_field_size
Return receptive field size.
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:202
Methodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000,
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:108
Methodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000,
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:491
Methodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000,
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:112
Functionregister_txt_processors
(name)
NeuralSeq/data_gen/tts/txt_processors/base_text_processor.py:5
Functionregister_vocoder
(cls)
NeuralSeq/vocoders/base_vocoder.py:5
Functionregister_wav_processors
(name)
NeuralSeq/data_gen/tts/wav_processors/base_processor.py:4
Functionrelu_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:189
Functionremove_padding
(x, padding_idx=0)
NeuralSeq/utils/__init__.py:212
Methodremove_weight_norm
(self)
NeuralSeq/modules/GenerSpeech/model/wavenet.py:80
Methodremove_weight_norm
(m)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:722
Methodremove_weight_norm
(self)
NeuralSeq/modules/hifigan/hifigan.py:89
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:291
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:425
Methodremove_weight_norm
Remove weight normalization module from all of the layers.
NeuralSeq/modules/parallel_wavegan/models/melgan.py:395
Methodremove_weight_norm
(m)
NeuralSeq/modules/syntaspeech/syntaspeech.py:266
Methodremove_weight_norm
(self)
NeuralSeq/modules/commons/wavenet.py:90
Methodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:81
Methodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:129
Methodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:83
Methodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:128
Methodremove_weight_norm
(self)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:205
Methodrepeat_wat2img
(self, x, cur_pos)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:851
Methodrescale_bbox
(bbox)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:552
Methodrescale_bbox
(bbox)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:880
Methodrescale_bbox
(bbox)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:562
Methodreset_parameters
Reset parameters.
NeuralSeq/modules/parallel_wavegan/layers/residual_block.py:22
Methodreset_parameters
Reset parameters.
NeuralSeq/modules/parallel_wavegan/layers/upsample.py:54
Methodreset_parameters
Reset parameters.
NeuralSeq/modules/commons/espnet_positional_embedding.py:73
Functionrgb2ycbcr
same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:529
Methodrun_image_or_audio
(self, file, state, txt)
audio-chatgpt.py:1250
Methodrun_text
(self, text, state)
audio-chatgpt.py:1197
Methodsample
(self)
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:6
Methodsample
(self)
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:35
Methodsample
(self, S, batch_size, shape, conditioning=None,
text_to_audio/Make_An_Audio/ldm/models/diffusion/plms.py:58
Methodsample_gumbel
(shape, eps=1e-20)
audio_to_text/captioning/models/base_model.py:216
Methodsave_checkpoint
(self, filepath)
NeuralSeq/utils/pl_utils.py:739
Functionsave_json
(data, name="data.json")
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:309
Functionsave_p
(obj, filename)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:283
Methodsave_result
(wav_out, mel, base_fn, gen_dir, str_phs=None, mel2ph=None, alignment=None)
NeuralSeq/modules/GenerSpeech/task/generspeech.py:232
Methodsave_result
(wav_out, mel, base_fn, gen_dir, str_phs=None, mel2ph=None, alignment=None)
NeuralSeq/tasks/tts/tts_base.py:247
Methodsave_result
(wav_out, mel, prefix, item_name, text, gen_dir, str_phs=None, mel2ph=None, gt_f0=None, pred_f0=None)
NeuralSeq/tasks/tts/fs2.py:459
Methodsave_valid_result
(self, sample, batch_idx, model_out)
NeuralSeq/tasks/tts/ps.py:104
Methodsave_valid_result
(self, sample, batch_idx, model_out)
NeuralSeq/tasks/tts/ps_flow.py:99
Functionscale_module
Scale the parameters of a module and return it.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/util.py:183
Methodschedule
(self, n, **kwargs)
text_to_audio/Make_An_Audio/ldm/lr_scheduler.py:83
Methodseq_forward
(self, input_dict)
audio_to_text/captioning/models/transformer_model.py:20
← previousnext →2,501–2,600 of 2,752, ranked by callers