MCPcopy Create free account

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

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

Methodevaluate_mertics
(self, pred, target)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/loss.py:279
Functionexist
Check if dataset exists
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/utils.py:83
Methodextra_repr
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:359
Methodextra_repr
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:482
Methodextra_repr
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:526
Methodextra_repr
(self)
text_to_audio/Make_An_Audio/ldm/modules/encoders/open_clap/htsat.py:594
Methodextract
Input: (batch_size, times_steps, freq_bins)
audio_detection/target_sound_detection/src/models.py:660
Methodextract_originbert
(self, caption_file: str, output: str, dev: bool=True, ip="localhost")
audio_to_text/captioning/utils/bert/create_sent_embedding.py:21
Methodextract_sbert
(self, input_json: str, output: str)
audio_to_text/captioning/utils/bert/create_sent_embedding.py:66
Methodextract_sentbert
(self, caption_file: str, output: str, dev: bool=True, zh: bool=False)
audio_to_text/captioning/utils/bert/create_sent_embedding.py:10
Functionfeature_loss
(fmap_r, fmap_g)
NeuralSeq/modules/hifigan/hifigan.py:328
Functionfeature_loss
(fmap_r, fmap_g)
text_to_audio/Make_An_Audio/vocoder/hifigan/modules.py:262
Functionfeature_loss
(fmap_r, fmap_g)
text_to_audio/Make_An_Audio/vocoder/bigvgan/models.py:358
Functionfill_with_neg_inf
FP16-compatible function that fills a tensor with -inf.
NeuralSeq/utils/tts_utils.py:63
Functionfill_with_neg_inf2
FP16-compatible function that fills a tensor with -inf.
NeuralSeq/utils/tts_utils.py:68
Functionfind_files
Find files recursively. Args: root_dir (str): Root root_dir to find. query (str): Query to find. include_root_dir (bool):
NeuralSeq/modules/parallel_wavegan/utils/utils.py:17
Functionfix_batchnorm
(model: torch.nn.Module)
audio_to_text/captioning/utils/train_util.py:122
Methodforward
:param ctx: autograd context :param input: input signal (B x 2 x T) :param warpfield: the corresponding warpfield (B x 2 x T)
mono2binaural/src/warping.py:17
Methodforward
:param input: audio signal to be warped (B x 2 x T) :param warpfield: the corresponding warpfield (B x 2 x T) :return: the wa
mono2binaural/src/warping.py:76
Methodforward
:param input: audio signal to be warped (B x 2 x T) :param displacements: sequence of 3D displacement vectors for geometric warping (
mono2binaural/src/warping.py:103
Methodforward
:param mono: input signal as tensor of shape B x 1 x T :param view: rx/tx position/orientation as tensor of shape B x 7 x K (K = T /
mono2binaural/src/models.py:45
Methodforward
:param mono: input signal as tensor of shape B x 1 x T :param view: rx/tx position/orientation as tensor of shape B x 7 x K (K = T /
mono2binaural/src/models.py:72
Methodforward
:param mono: the input signal as a B x 1 x T tensor :param view: the receiver/transmitter position as a B x 7 x T tensor :ret
mono2binaural/src/models.py:98
Methodforward
(self, txt_tokens, mel2ph=None, ref_mel2ph=None, ref_mel2word=None, spk_embed=None, emo_embed=None, ref_mels=N
NeuralSeq/modules/GenerSpeech/model/generspeech.py:75
Methodforward
(self, x, spk_embed)
NeuralSeq/modules/GenerSpeech/model/mixstyle.py:37
Methodforward
(self, x, x_mask=None, g=None, **kwargs)
NeuralSeq/modules/GenerSpeech/model/wavenet.py:54
Methodforward
:param x: [B, T, D] :return: [B, T, D]
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:47
Methodforward
(self, src, local_emotion, emotion_key_padding_mask=None, forcing=False)
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:107
Methodforward
(self, src, local_emotion, src_key_padding_mask=None, emotion_key_padding_mask=None, forcing=False)
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:138
Methodforward
:param ref_mels: [B, T, 80] :return: [B, 1, H]
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:182
Methodforward
(self, x)
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:209
Methodforward
(self, x)
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:264
Methodforward
:param x: [B, T, H] :return: [B, T, H]
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:324
Methodforward
:param txt_tokens: [B, T] :return: { 'encoder_out': [B x T x C] }
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:348
Methodforward
(self, x, g, x_mask)
NeuralSeq/modules/GenerSpeech/model/prosody_util.py:372
Methodforward
(self, x)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:20
Methodforward
(self, x, x_mask)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:57
Methodforward
(self, x, x_mask=None, reverse=False, **kwargs)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:77
Methodforward
(self, x, x_mask=None, reverse=False, **kwargs)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:147
Methodforward
log-det = log|abs(|W|)| * pixels
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:242
Methodforward
(self, x, x_mask=None, reverse=False, g=None, **kwargs)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:311
Methodforward
:param x: [B, C_x, T] :param x_mask: [B, 1, T] :param g: [B, C_g, T] :return: [B, C_x, T]
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:346
Methodforward
(self, x, x_mask=None, reverse=False, g=None, **kwargs)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:386
Methodforward
(self, x, x_mask=None, reverse=False, g=None, **kwargs)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:452
Methodforward
(self, x, x_mask=None, g=None, reverse=False, return_hiddens=False)
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:556
Methodforward
(self, x=None, x_mask=None, g=None, reverse=False, concat_zs=True, noise_scale=0.66, return_hi
NeuralSeq/modules/GenerSpeech/model/glow_modules.py:648
Methodforward
(self, x)
NeuralSeq/modules/hifigan/hifigan.py:54
Methodforward
(self, x)
NeuralSeq/modules/hifigan/hifigan.py:82
Methodforward
(self, x, f0=None)
NeuralSeq/modules/hifigan/hifigan.py:144
Methodforward
(self, x, mel)
NeuralSeq/modules/hifigan/hifigan.py:202
Methodforward
(self, y, y_hat, mel=None)
NeuralSeq/modules/hifigan/hifigan.py:237
Methodforward
(self, x, mel)
NeuralSeq/modules/hifigan/hifigan.py:273
Methodforward
(self, y, y_hat, mel=None)
NeuralSeq/modules/hifigan/hifigan.py:309
Methodforward
:param txt_tokens: [B, T] :return: { 'encoder_out': [T x B x C] }
NeuralSeq/modules/diffsinger_midi/fs2.py:25
Methodforward
(self, x)
NeuralSeq/modules/diff/net.py:37
Methodforward
(self, x, conditioner, diffusion_step)
NeuralSeq/modules/diff/net.py:66
Methodforward
:param spec: [B, 1, M, T] :param diffusion_step: [B, 1] :param cond: [B, M, T] :return:
NeuralSeq/modules/diff/net.py:107
Methodforward
(self, x, *args, **kwargs)
NeuralSeq/modules/diff/diffusion.py:49
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:58
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:69
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:78
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:87
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:97
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:112
Methodforward
(self, x, time_emb)
NeuralSeq/modules/diff/diffusion.py:128
Methodforward
(self, x)
NeuralSeq/modules/diff/diffusion.py:143
Methodforward
(self, txt_tokens, mel2ph=None, spk_embed=None, ref_mels=None, f0=None, uv=None, energy=None,
NeuralSeq/modules/diff/diffusion.py:300
Methodforward
(self, x)
NeuralSeq/modules/diff/candidate_decoder.py:19
Methodforward
:param spec: [B, 1, 80, T] :param diffusion_step: [B, 1] :param cond: [B, M, T] :return:
NeuralSeq/modules/diff/candidate_decoder.py:50
Methodforward
(self, txt_tokens, mel2ph=None, spk_embed=None, ref_mels=None, f0=None, uv=None, energy=None,
NeuralSeq/modules/diff/shallow_diffusion_tts.py:233
Methodforward
(self, txt_tokens, mel2ph=None, spk_embed=None, ref_mels=None, f0=None, uv=None, energy=None,
NeuralSeq/modules/diff/shallow_diffusion_tts.py:293
Methodforward
(self, x, **kwargs)
NeuralSeq/modules/fastspeech/tts_modules.py:30
Methodforward
Calculate forward propagation. Args: xs (Tensor): Batch of input sequences (B, Tmax, idim). x_masks (ByteTensor, optio
NeuralSeq/modules/fastspeech/tts_modules.py:125
Methodforward
(self, x, x_padding=None, ph2word=None, graph_lst=None, etypes_lst=None)
NeuralSeq/modules/fastspeech/tts_modules.py:163
Methodforward
Example (no batch dim version): 1. dur = [2,2,3] 2. token_idx = [[1],[2],[3]], dur_cumsum = [2,4,7], dur_cumsum_prev
NeuralSeq/modules/fastspeech/tts_modules.py:184
Methodforward
:param xs: [B, T, H] :return: [B, T, H]
NeuralSeq/modules/fastspeech/tts_modules.py:247
Methodforward
:param x: [B, T, C] :param padding_mask: [B, T] :return: [B, T, C] or [L, B, T, C]
NeuralSeq/modules/fastspeech/tts_modules.py:307
Methodforward
:param txt_tokens: [B, T] :return: { 'encoder_out': [T x B x C] }
NeuralSeq/modules/fastspeech/tts_modules.py:352
Methodforward
(self, txt_tokens, mel2ph=None, spk_embed=None, ref_mels=None, f0=None, uv=None, energy=None,
NeuralSeq/modules/fastspeech/fs2.py:79
Methodforward
:param x: [B, T, 80] :return: [L, B, T, H], [B, T, H]
NeuralSeq/modules/fastspeech/pe.py:23
Methodforward
:param x: [B, C, T] :return: [B, C, T]
NeuralSeq/modules/fastspeech/pe.py:62
Methodforward
:param x: [B, T, H] :return: [B, T, H]
NeuralSeq/modules/fastspeech/pe.py:98
Methodforward
(self, mel_input=None)
NeuralSeq/modules/fastspeech/pe.py:135
Methodforward
Calculate forward propagation. Args: x (Tensor): Predicted signal (B, T). y (Tensor): Groundtruth signal (B, T).
NeuralSeq/modules/parallel_wavegan/stft_loss.py:29
Methodforward
Calculate forward propagation. Args: x (Tensor): Predicted signal (B, T). y (Tensor): Groundtruth signal (B, T).
NeuralSeq/modules/parallel_wavegan/stft_loss.py:79
Methodforward
Calculate forward propagation. Args: x (Tensor): Input tensor (B, residual_channels, T). c (Tensor): Local conditioni
NeuralSeq/modules/parallel_wavegan/layers/residual_block.py:91
Methodforward
Calculate forward propagation. Args: c (Tensor): Input tensor (B, channels, T). Returns: Tensor: Output tens
NeuralSeq/modules/parallel_wavegan/layers/residual_stack.py:65
Methodforward
Calculate forward propagation. Args: x (Tensor): Input tensor (B, C, F, T). Returns: Tensor: Interpolated te
NeuralSeq/modules/parallel_wavegan/layers/upsample.py:33
Methodforward
Calculate forward propagation. Args: c : Input tensor (B, C, T). Returns: Tensor: Upsampled tensor (B, C, T'
NeuralSeq/modules/parallel_wavegan/layers/upsample.py:106
Methodforward
Calculate forward propagation. Args: c : Input tensor (B, C, T'). Returns: Tensor: Upsampled tensor (B, C, T
NeuralSeq/modules/parallel_wavegan/layers/upsample.py:167
Methodforward
Calculate forward propagation. Args: x (Tensor): Input tensor (B, in_channels, T). Returns: Tensor: Output t
NeuralSeq/modules/parallel_wavegan/layers/causal_conv.py:23
Methodforward
Calculate forward propagation. Args: x (Tensor): Input tensor (B, in_channels, T_in). Returns: Tensor: Outpu
NeuralSeq/modules/parallel_wavegan/layers/causal_conv.py:46
Methodforward
Calculate forward propagation. Args: x (Tensor): Input noise signal (B, C_in, T). c (Tensor): Local conditioning
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:138
Methodforward
Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: Tensor: Output
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:268
Methodforward
Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: Tensor: Output
NeuralSeq/modules/parallel_wavegan/models/parallel_wavegan.py:392
Methodforward
Calculate forward propagation. Args: c (Tensor): Input tensor (B, channels, T). Returns: Tensor: Output tens
NeuralSeq/modules/parallel_wavegan/models/melgan.py:147
Methodforward
Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: List: List of output
NeuralSeq/modules/parallel_wavegan/models/melgan.py:285
Methodforward
Calculate forward propagation. Args: x (Tensor): Input noise signal (B, 1, T). Returns: List: List of list o
NeuralSeq/modules/parallel_wavegan/models/melgan.py:378
Methodforward
sine_tensor, uv = forward(f0) input F0: tensor(batchsize=1, length, dim=1) f0 for unvoiced steps should be 0 output
NeuralSeq/modules/parallel_wavegan/models/source.py:104
Methodforward
Pulse train generator pulse_train, uv = forward(f0) input F0: tensor(batchsize=1, length, dim=1) f0 for unvoiced st
NeuralSeq/modules/parallel_wavegan/models/source.py:158
← previousnext →1,901–2,000 of 2,752, ranked by callers