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
↓ 7 callersMethodadd_mel_loss
(self, mel_out, target, losses, postfix='', mel_mix_loss=None)
NeuralSeq/tasks/tts/fs2.py:141
↓ 7 callersFunctionf0_to_coarse
(f0)
NeuralSeq/utils/pitch_utils.py:22
↓ 7 callersFunctiongenerate_length_mask
(lens, max_length=None)
audio_to_text/captioning/models/utils.py:29
↓ 7 callersMethodget_learned_conditioning
(self, c)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:549
↓ 7 callersMethodget_learned_conditioning
(self, c)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:170
↓ 7 callersMethodget_loss
(self, pred, target, mean=True)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:277
↓ 7 callersFunctionget_vocoder_cls
(hparams)
NeuralSeq/vocoders/base_vocoder.py:11
↓ 7 callersFunctioninit_bn
Initialize a Batchnorm layer.
sound_extraction/model/modules.py:439
↓ 7 callersFunctioninit_bn
Initialize a Batchnorm layer.
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/pann_model.py:26
↓ 7 callersMethodinit_hidden
(self, bs, device)
audio_to_text/captioning/models/decoder.py:62
↓ 7 callersFunctionmake_attn
(in_channels, attn_type="vanilla")
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/model.py:205
↓ 7 callersFunctionmel2ph_to_dur
(mel2ph, T_txt, max_dur=None)
NeuralSeq/modules/fastspeech/tts_modules.py:267
↓ 7 callersFunctionnum2chn
(number_string, numbering_type=NUMBERING_TYPES[1], big=False, traditional=False, alt_zero=False, a
NeuralSeq/utils/text_norm.py:319
↓ 7 callersMethodprocess
(self)
NeuralSeq/data_gen/tts/base_binarizer.py:111
↓ 7 callersMethodquantize
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:468
↓ 7 callersFunctionrepeat_tensor
(x, n)
audio_to_text/captioning/models/utils.py:76
↓ 7 callersMethodresample
Resample. Args: waveform: (clip_samples,) Returns: (resampled_clip_samples,)
audio_detection/audio_infer/utils/data_generator.py:55
↓ 6 callersMethod__init__
(self, dim_in, dim_out)
text_to_audio/Make_An_Audio/ldm/modules/attention.py:38
↓ 6 callersMethod__init__
(self, h, channels, kernel_size=3, dilation=(1, 3, 5))
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:23
↓ 6 callersMethod__init__
(self, h)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:135
↓ 6 callersFunctionadd_JPEG_noise
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:418
↓ 6 callersFunctionadd_blur
(img, sf=4)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:325
↓ 6 callersMethodadd_energy_loss
(self, energy_pred, energy, losses)
NeuralSeq/tasks/tts/fs2.py:277
↓ 6 callersMethodadd_pitch_loss
(self, output, sample, losses)
NeuralSeq/tasks/tts/fs2.py:219
↓ 6 callersFunctionappend_to_dict
(dict, key, value)
audio_detection/audio_infer/pytorch/pytorch_utils.py:34
↓ 6 callersMethodapply_model
(self, x_noisy, t, cond, return_ids=False)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:889
↓ 6 callersFunctionbuild_token_encoder
(token_list_file)
NeuralSeq/data_gen/tts/data_gen_utils.py:355
↓ 6 callersFunctionconvert_pad_shape
(pad_shape)
NeuralSeq/modules/commons/rel_transformer.py:11
↓ 6 callersFunctiondefault
(val, d)
text_to_audio/Make_An_Audio/ldm/modules/x_transformer.py:58
↓ 6 callersFunctiondo_mixup
Mixup x of even indexes (0, 2, 4, ...) with x of odd indexes (1, 3, 5, ...). Args: x: (batch_size * 2, ...) mixup_lambda: (batch
audio_detection/audio_infer/pytorch/pytorch_utils.py:18
↓ 6 callersMethodencode_audio
(self, audio, device)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:590
↓ 6 callersFunctionget_filename
(path)
audio_detection/audio_infer/utils/utilities.py:18
↓ 6 callersFunctionget_lf0_cwt
input: signal of shape (N) output: Wavelet_lf0 of shape(10, N), scales of shape(10)
NeuralSeq/utils/cwt.py:53
↓ 6 callersMethodinfer_once
(self, inp)
NeuralSeq/inference/svs/base_svs_infer.py:228
↓ 6 callersFunctioninit_layer
Initialize a Linear or Convolutional layer.
audio_detection/target_sound_detection/src/models.py:137
↓ 6 callersFunctioninit_layer
Initialize a Linear or Convolutional layer.
audio_detection/audio_infer/pytorch/models.py:97
↓ 6 callersFunctionmel2token_to_dur
(mel2token, T_txt=None, max_dur=None)
NeuralSeq/utils/tts_utils.py:373
↓ 6 callersFunctionmetrics
Adapted from https://github.com/hche11/VGGSound/blob/master/utils.py Calculate statistics including mAP, AUC, and d-prime. Args:
text_to_audio/Make_An_Audio/ldm/modules/losses_audio/vggishish/metrics.py:10
↓ 6 callersMethodmode
(self)
text_to_audio/Make_An_Audio/ldm/modules/distributions/distributions.py:20
↓ 6 callersFunctionnoise_like
(shape, device, repeat=False)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/util.py:264
↓ 6 callersMethodparse
(self, clean_sentence=None, words=None, ph_words=None)
NeuralSeq/modules/syntaspeech/syntactic_graph_buider.py:15
↓ 6 callersMethodsample_log
(self,cond,batch_size,ddim, ddim_steps,**kwargs)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:905
↓ 5 callersMethod__init__
(self, samp_rate, harmonic_num=0, sine_amp=0.1, noise_std=0.003, voiced_thre
NeuralSeq/modules/parallel_wavegan/models/source.py:25
↓ 5 callersMethod__init__
(self, sample_rate, window_size, hop_size, mel_bins, fmin, fmax, classes_num, enable_fusion=False, fus
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/pann_model.py:334
↓ 5 callersMethodadd_dur_loss
(self, dur_pred, mel2token, word_len, txt_tokens, losses=None)
NeuralSeq/tasks/tts/ps.py:85
↓ 5 callersMethodadd_word
(self, word)
audio_to_text/captioning/utils/build_vocab.py:17
↓ 5 callersMethodadd_word
(self, word)
audio_to_text/captioning/utils/build_vocab_ltp.py:16
↓ 5 callersMethodadd_word
(self, word)
audio_to_text/captioning/utils/build_vocab_spacy.py:16
↓ 5 callersMethodcardinal2chntext
(self)
NeuralSeq/utils/text_norm.py:431
↓ 5 callersFunctioncoco_score
(refs, pred, scorer)
audio_to_text/captioning/utils/model_eval_diff.py:13
↓ 5 callersFunctiondo_mixup
Args: x: (batch_size , ...) mixup_lambda: (batch_size,) Returns: out: (batch_size, ...)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:176
↓ 5 callersMethodencode_text
(self, text, device)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:603
↓ 5 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:295
↓ 5 callersMethodget_input
(self, batch, k)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:327
↓ 5 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:273
↓ 5 callersFunctioninit_bn
Initialize a Batchnorm layer.
audio_detection/audio_infer/pytorch/models.py:106
↓ 5 callersFunctioninterpolate
Interpolate data in time domain. This is used to compensate the resolution reduction in downsampling of a CNN. Args: x: (batch_siz
audio_detection/audio_infer/pytorch/pytorch_utils.py:103
↓ 5 callersFunctioninterpolate
Interpolate data in time domain. This is used to compensate the resolution reduction in downsampling of a CNN. Args: x: (batch_size, ti
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:191
↓ 5 callersMethodis_function_implemented
(self, f_name)
NeuralSeq/utils/pl_utils.py:1606
↓ 5 callersFunctionismap
(x)
text_to_audio/Make_An_Audio/ldm/util.py:74
↓ 5 callersFunctionload_data
(hdf5_path)
audio_detection/audio_infer/utils/plot_statistics.py:1517
↓ 5 callersFunctionnorm_interp_f0
(f0, hparams)
NeuralSeq/utils/pitch_utils.py:45
↓ 5 callersFunctionnum_params
(model, print_out=True, model_name="model")
NeuralSeq/utils/__init__.py:245
↓ 5 callersMethodoutput_fn
(self, input_fn)
NeuralSeq/data_gen/tts/wav_processors/base_processor.py:21
↓ 5 callersMethodprocess_item
(cls, item_name, ph, txt, tg_fn, wav_fn, spk_id, encoder, binarization_args)
NeuralSeq/data_gen/tts/base_binarizer.py:160
↓ 5 callersFunctionremove_file
(*fns)
NeuralSeq/utils/os_utils.py:18
↓ 5 callersMethodrun_model
(self, sample, infer=False, *args, **kwargs)
NeuralSeq/tasks/tts/ps_adv.py:104
↓ 5 callersFunctionsave_wav
(wav, path, sr, norm=False)
NeuralSeq/utils/audio.py:12
↓ 5 callersMethodtrain
(self)
NeuralSeq/utils/pl_utils.py:1313
↓ 5 callersMethodtraining_step
(self, sample, batch_idx, optimizer_idx=-1)
NeuralSeq/tasks/base_task.py:127
↓ 5 callersMethodtxt_to_ph
(txt_processor, txt_raw, preprocess_args)
NeuralSeq/data_gen/tts/base_preprocess.py:147
↓ 5 callersMethodvalidation_step
:param sample: :param batch_idx: :return: output: dict
NeuralSeq/tasks/base_task.py:169
↓ 5 callersFunctionzero_module
Zero out the parameters of a module and return it.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/util.py:174
↓ 4 callersMethod__init__
(self, hidden_size, out_dims, dilations, kernel_size, norm_type='ln', layers_in_block=2, c_mu
NeuralSeq/modules/commons/conv.py:72
↓ 4 callersMethod__init__
(self, in_channels, hidden_channels, kernel_size,
NeuralSeq/modules/commons/normalizing_flow/glow_modules.py:269
↓ 4 callersMethod__init__
(self, emb_dim, vocab_size=527)
audio_to_text/captioning/models/transformer_model.py:170
↓ 4 callersMethod_f02uv
(self, f0)
NeuralSeq/modules/parallel_wavegan/models/source.py:38
↓ 4 callersMethod_get_item
(self, index)
NeuralSeq/tasks/tts/pe.py:41
↓ 4 callersMethod_in_proj
(self, input, start=0, end=None)
NeuralSeq/modules/commons/transformer.py:452
↓ 4 callersMethod_in_proj
(self, input, start=0, end=None)
NeuralSeq/modules/commons/common_layers.py:453
↓ 4 callersMethod_make_layer
(self, planes, blocks, stride=1)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/model.py:192
↓ 4 callersFunction_ntuple
(n)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:30
↓ 4 callersFunction_plot_4_rows
(x, ax, ax2, ax3, ax4, c, linewidth=1.0, alpha=1.0, label="")
audio_detection/audio_infer/utils/plot_statistics.py:1774
↓ 4 callersFunction_plot_4_rows
(x, ax, ax2, ax3, ax4, c, linewidth=1.0, alpha=1.0, label="")
audio_detection/audio_infer/utils/plot_for_paper.py:531
↓ 4 callersFunction_scatter_4_rows
(x, ax, ax2, ax3, ax4, s, c, marker='.', alpha=1.)
audio_detection/audio_infer/utils/plot_statistics.py:1767
↓ 4 callersFunction_scatter_4_rows
(x, ax, ax2, ax3, ax4, s, c, marker='.', alpha=1.)
audio_detection/audio_infer/utils/plot_for_paper.py:523
↓ 4 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:369
↓ 4 callersFunctionadd_JPEG_noise
(img)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:422
↓ 4 callersFunctionbuild_phone_encoder
(data_dir)
NeuralSeq/data_gen/tts/data_gen_utils.py:340
↓ 4 callersFunctioncalculate_weights_indices
(in_length, out_length, scale, kernel, kernel_width, antialiasing)
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/utils_image.py:708
↓ 4 callersFunctionchn2num
(chinese_string, numbering_type=NUMBERING_TYPES[1])
NeuralSeq/utils/text_norm.py:233
↓ 4 callersMethodcompute_top_k
(self, logits, labels, k, reduction="mean")
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:150
↓ 4 callersMethodcreate
(cls, index, value, numbering_type=NUMBERING_TYPES[1], small_unit=False)
NeuralSeq/utils/text_norm.py:94
↓ 4 callersFunctionembedding_pooling
(x, lens, pooling="mean")
audio_to_text/captioning/models/encoder.py:150
↓ 4 callersMethodencode_first_stage
(self, x)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:468
↓ 4 callersMethodeos
(self)
NeuralSeq/utils/text_encoder.py:281
↓ 4 callersFunctionexpand_states
(h, mel2token)
NeuralSeq/modules/commons/align_ops.py:21
↓ 4 callersMethodextend_pe
Reset the positional encodings.
NeuralSeq/modules/commons/espnet_positional_embedding.py:24
↓ 4 callersFunctionf0_to_figure
(f0_gt, f0_cwt=None, f0_pred=None)
NeuralSeq/utils/plot.py:45
↓ 4 callersMethodfinalize
(self)
NeuralSeq/utils/indexed_datasets.py:52
← previousnext →101–200 of 2,752, ranked by callers