MCPcopy Create free account

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

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

Functioncollate_fn
Collate data. Args: list_data_dict, e.g., [{'audio_name': str, 'waveform': (clip_samples,), ...}, {'audio_name
audio_detection/audio_infer/utils/data_generator.py:406
Methodcollater
(self, samples)
NeuralSeq/modules/GenerSpeech/task/dataset.py:146
Methodcollater
(self, samples)
NeuralSeq/tasks/base_task.py:45
Methodcollater
(self, samples)
NeuralSeq/tasks/svs/diffsinger_task.py:114
Methodcollater
(self, samples)
NeuralSeq/tasks/svs/diffsinger_task.py:264
Methodcollater
(self, samples)
NeuralSeq/tasks/tts/fs2_utils.py:105
Methodcollater
(self, samples)
NeuralSeq/tasks/tts/dataset_utils.py:187
Methodcollater
(self, samples)
NeuralSeq/tasks/tts/dataset_utils.py:249
Methodcollater
(self, samples)
NeuralSeq/tasks/tts/pe.py:70
Methodcollater
(self, batch)
NeuralSeq/tasks/vocoder/dataset_utils.py:100
Functioncond_discriminator_loss
(outputs)
NeuralSeq/modules/hifigan/hifigan.py:350
Methodconfigure_optimizers
(self)
NeuralSeq/tasks/tts/fs2_adv.py:95
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:217
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:417
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:144
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:1037
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:220
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:413
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:1359
Methodconfigure_optimizers
(self)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:1049
Functionconnect_clusters
(x, n=1)
audio_detection/target_sound_detection/src/utils.py:293
Functionconv1d_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:162
Functionconv2d_hook
(self, input, output)
audio_detection/audio_infer/pytorch/pytorch_utils.py:149
Functionconvert_module_to_f16
(x)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:24
Functionconvert_module_to_f32
(x)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:27
Methodconvert_to_fp16
Convert the torso of the model to float16.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:695
Methodconvert_to_fp16
Convert the torso of the model to float16.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:926
Methodconvert_to_fp16
Convert the torso of the model to float16.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/custom_openaimodel.py:315
Methodconvert_to_fp32
Convert the torso of the model to float32.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:703
Methodconvert_to_fp32
Convert the torso of the model to float32.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:933
Methodconvert_to_fp32
Convert the torso of the model to float32.
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/custom_openaimodel.py:323
Functioncopy_file
(from_file, to_file)
NeuralSeq/utils/os_utils.py:14
Functioncount_flops
Count flops. Code modified from others' implementation.
audio_detection/audio_infer/pytorch/pytorch_utils.py:144
Methodcount_flops
(model, _x, y)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:375
Methodcount_flops
(model, _x, y)
text_to_audio/Make_An_Audio/ldm/modules/diffusionmodules/openaimodel.py:409
Functioncount_parameters
(model)
audio_detection/audio_infer/pytorch/pytorch_utils.py:140
Methodcreate
(cls, i, v)
NeuralSeq/utils/text_norm.py:130
Functioncreate_embedding
(caption_file: str, vocab_file: str, embed_size: int,
audio_to_text/captioning/utils/fasttext/create_word_embedding.py:16
Functioncreate_embedding
(vocab_file: str, embed_size: int, output: str,
audio_to_text/captioning/utils/word2vec/create_word_embedding.py:17
Functioncreate_model_and_transforms
( model_name: str, pretrained: str = "", precision: str = "fp32", device: torch.device = torch
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/factory.py:224
Methodcrop_wav
(self, x, crop_size, spe_pos = None)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:821
Methodcwt2f0_norm
(self, cwt_spec, mean, std, mel2ph)
NeuralSeq/modules/diff/diffusion.py:330
Methodcwt2f0_norm
(self, cwt_spec, mean, std, mel2ph)
NeuralSeq/modules/diff/shallow_diffusion_tts.py:285
Functioncycle
(dl)
NeuralSeq/modules/diff/diffusion.py:29
Functiondata_loader
Decorator to make any fx with this use the lazy property :param fn: :return:
NeuralSeq/utils/pl_utils.py:47
Methoddata_parallel
(self)
NeuralSeq/utils/pl_utils.py:466
Methodddp_train
Entry point into a DP thread :param gpu_idx: :param model: :param cluster_obj: :return:
NeuralSeq/utils/pl_utils.py:847
Methoddecode
(self, ids, strip_extraneous=False)
NeuralSeq/utils/text_encoder.py:117
Methoddecode
(self, ids, strip_eos=False, strip_padding=False)
NeuralSeq/utils/text_encoder.py:207
Methoddecode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:77
Methoddecode
(self, h, force_not_quantize=False)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:294
Methoddecode
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:465
Methoddecode
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:192
Methoddecode_code
(self, code_b)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:112
Methoddecode_list
(self, ids)
NeuralSeq/utils/text_encoder.py:133
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:442
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:438
Functiondegradation_bsrgan_plus
This is an extended degradation model by combining the degradation models of BSRGAN and Real-ESRGAN ---------- img: HXWXC, [0, 1], it
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:617
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan_light.py:534
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
text_to_audio/Make_An_Audio/ldm/modules/image_degradation/bsrgan.py:530
Functiondenormalize
(D, hparams)
NeuralSeq/utils/audio.py:58
Methoddifferentiable_decode_first_stage
(self, z, predict_cids=False, force_not_quantize=False)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio.py:412
Methoddifferentiable_decode_first_stage
(self, z, predict_cids=False, force_not_quantize=False)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:764
Methoddifferentiable_decode_first_stage
(self, z, predict_cids=False, force_not_quantize=False)
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm_audio_inpaint.py:408
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:138
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
text_to_audio/Make_An_Audio/ldm/models/diffusion/classifier.py:22
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
text_to_audio/Make_An_Audio/ldm/models/diffusion/ddpm.py:33
Methoddiscriminator_block
Input: (B, in, 2H, 2W) Output:(B, out, H, W)
text_to_audio/Make_An_Audio/ldm/modules/discriminator/multi_window_disc.py:12
Functiondiscriminator_loss
(disc_real_outputs, disc_generated_outputs)
NeuralSeq/modules/hifigan/hifigan.py:337
Functiondiscriminator_loss
(disc_real_outputs, disc_generated_outputs)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:271
Functiondiscriminator_loss
(disc_real_outputs, disc_generated_outputs)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:367
Methoddo_gradient_ops
(self)
NeuralSeq/data_gen/tts/emotion/model.py:33
Functiondouble_threshold
double_threshold Helper function to calculate double threshold for n-dim arrays :param x: input array :param high_thres: high threshold v
audio_detection/target_sound_detection/src/utils.py:238
Functiondpsr_degradation
bicubic downsampling + blur 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:262
Functiondpsr_degradation
bicubic downsampling + blur 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:262
Functiondynamic_range_compression
(x, C=1, clip_val=1e-5)
NeuralSeq/modules/hifigan/mel_utils.py:15
Functiondynamic_range_decompression
(x, C=1)
NeuralSeq/modules/hifigan/mel_utils.py:19
Functionembed_speaker
(wavs, **kwargs)
NeuralSeq/data_gen/tts/emotion/inference.py:158
Functionembed_utterance
Computes an embedding for a single utterance. # TODO: handle multiple wavs to benefit from batching on GPU :param wav: a preprocesse
NeuralSeq/data_gen/tts/emotion/inference.py:111
Functionembedding_score
(refs, pred, scorer)
audio_to_text/captioning/utils/model_eval_diff.py:40
Methodencode
(self, s)
NeuralSeq/utils/text_encoder.py:108
Methodencode
(self, s)
NeuralSeq/utils/text_encoder.py:153
Methodencode
Converts a space-separated string of tokens to a list of ids.
NeuralSeq/utils/text_encoder.py:197
Methodencode
(self, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:18
Methodencode
(self, x)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:50
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:71
Methodencode
(self, x)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:135
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:169
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:205
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:237
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:280
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:313
Methodencode
(self, text)
text_to_audio/Make_An_Audio/ldm/modules/encoders/modules.py:349
Methodencode
(self, x)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:289
Methodencode
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:462
Methodencode
(self, x, *args, **kwargs)
text_to_audio/Make_An_Audio/ldm/models/autoencoder_multi.py:189
Functionencode_labels
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:139
Methodencode_to_prequant
(self, x)
text_to_audio/Make_An_Audio/ldm/models/autoencoder.py:102
Methodeval_annotation
(self, annotation, output)
audio_to_text/captioning/utils/eval_round_robin.py:54
Methodeval_prediction
(self, prediction, annotation, output)
audio_to_text/captioning/utils/eval_round_robin.py:108
← previousnext →1,801–1,900 of 2,752, ranked by callers