MCPcopy Create free account

hub / github.com/RVC-Boss/GPT-SoVITS / functions

Functions1,613 in github.com/RVC-Boss/GPT-SoVITS

⨍ Functions 1,613◇ Types & classes 352↳ Endpoints 10
↓ 461 callersMethodto
(self, *arg, **kwargs)
tools/audio_sr.py:36
↓ 80 callersFunctionprocess_info
(process_name="", indicator="")
webui.py:244
↓ 53 callersMethodkeys
(self)
GPT_SoVITS/utils.py:331
↓ 31 callersMethodupdate
(self, input_pos: Tensor, k_val: Tensor, v_val: Tensor)
GPT_SoVITS/AR/models/t2s_model_cudagraph.py:93
↓ 29 callersMethodstft
(self, x)
tools/uvr5/mdxnet.py:35
↓ 25 callersMethodgetTexts
(text,default_lang = "")
GPT_SoVITS/text/LangSegmenter/langsegmenter.py:90
↓ 25 callersMethoditems
(self)
GPT_SoVITS/utils.py:334
↓ 23 callersMethodempty
(self)
GPT_SoVITS/AR/models/t2s_model_cudagraph.py:108
↓ 23 callersMethodresample
(self, ref_audio: torch.Tensor, src_sr: int, dst_sr: int)
GPT_SoVITS/export_torch_script.py:597
↓ 22 callersMethodforward
( self, x: Tensor, input_pos: Tensor, kv_cache: KVCacheNHD )
GPT_SoVITS/AR/models/t2s_model_cudagraph.py:139
↓ 20 callersMethodstep
Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model
GPT_SoVITS/AR/modules/optim.py:197
↓ 18 callersMethod__init__
(self, in_channels, dit)
GPT_SoVITS/module/models.py:1101
↓ 18 callersMethod__init__
( self, hidden_channels, kernel_size, dilation_rate, n_layers,
GPT_SoVITS/module/modules.py:133
↓ 18 callersFunctionget_padding
(kernel_size, dilation=1)
GPT_SoVITS/module/commons.py:12
↓ 18 callersFunctionget_phones_and_bert
(text, language, version, final=False)
GPT_SoVITS/inference_webui.py:640
↓ 17 callersMethod__init__
(self, in_channels, dit)
GPT_SoVITS/module/models_onnx.py:915
↓ 16 callersMethodempty_cache
(self)
GPT_SoVITS/TTS_infer_pack/TTS.py:1531
↓ 14 callersMethoddecode
(self, codes, text, refer, noise_scale=0.5, speed=1, sv_emb=None)
GPT_SoVITS/module/models.py:995
↓ 13 callersFunctionload_audio
(file, sr)
tools/my_utils.py:16
↓ 13 callersMethodrun
Text to speech inference. Args: inputs (dict): { "text": "", # str
GPT_SoVITS/TTS_infer_pack/TTS.py:998
↓ 12 callersMethodistft
(self, x, freq_pad=None)
tools/uvr5/mdxnet.py:50
↓ 12 callersFunctionkill_process
(pid, process_name="")
webui.py:234
↓ 12 callersFunctionnum2str
(value_string: str)
GPT_SoVITS/text/zh_normalization/num.py:317
↓ 11 callersMethod__init__
(self, dim)
GPT_SoVITS/f5_tts/model/modules.py:226
↓ 11 callersFunctioncleaned_text_to_sequence
Converts a string of text to a sequence of IDs corresponding to the symbols in the text. Args: text: string to convert to a sequence Ret
GPT_SoVITS/text/__init__.py:14
↓ 11 callersFunctionmerge_lang
(lang_list, item)
GPT_SoVITS/text/LangSegmenter/langsegmenter.py:69
↓ 10 callersMethod__init__
(self, vq_model: SynthesizerTrnV3, cfm: CFM, hps)
GPT_SoVITS/export_torch_script_v3v4.py:546
↓ 10 callersFunctioncheck_for_existance
(file_list: list = None, is_train=False, is_dataset_processing=False)
tools/my_utils.py:49
↓ 10 callersMethodextract_latent
(self, x)
GPT_SoVITS/module/models.py:266
↓ 10 callersFunctionfix_gpu_number
(input)
webui.py:145
↓ 10 callersFunctionmel_spectrogram_torch
(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False)
GPT_SoVITS/module/mel_processing.py:93
↓ 10 callersFunctionspectrogram_torch
(y, n_fft, sampling_rate, hop_size, win_size, center=False)
GPT_SoVITS/module/mel_processing.py:40
↓ 9 callersMethod__init__
(self, w1, b1, w2, b2)
GPT_SoVITS/export_torch_script.py:191
↓ 9 callersFunctionclean_path
(path_str: str)
tools/my_utils.py:40
↓ 9 callersMethodnormalize
(self, text: str)
GPT_SoVITS/text/zh_normalization/text_normlization.py:172
↓ 8 callersMethod__init__
( self, h: AttrDict, period: List[int], kernel_size: int = 5, stride:
GPT_SoVITS/BigVGAN/discriminators.py:22
↓ 8 callersFunctionb_save_file
()
tools/subfix_webui.py:262
↓ 8 callersMethoddecode_encp
(self, codes, text, refer, ge=None, speed=1)
GPT_SoVITS/module/models.py:1332
↓ 8 callersFunctionis_distributed
()
GPT_SoVITS/module/distrib.py:28
↓ 8 callersFunctionnormalize
!!! 所有的处理都需要正确的输入 !!! 可以添加新的处理，只需要添加正则表达式和对应的处理函数即可
GPT_SoVITS/text/en_normalization/expend.py:281
↓ 8 callersFunctionresamplex
(ref_audio: torch.Tensor, src_sr: int, dst_sr: int)
GPT_SoVITS/export_torch_script.py:835
↓ 7 callersMethod__init__
( self, dim: int, layer_scale_init_value=None, adanorm_num_embeddings=None,
tools/AP_BWE_main/models/model.py:36
↓ 7 callersMethod__init__
(self, dim)
tools/uvr5/bs_roformer/bs_roformer.py:47
↓ 7 callersMethod__init__
(self, dim)
tools/uvr5/bs_roformer/mel_band_roformer.py:56
↓ 7 callersMethod__init__
( self, in_channels, out_channels, filter_channels, kernel_size,
GPT_SoVITS/module/attentions.py:338
↓ 7 callersMethod_all_tone_three
(self, finals: List[str])
GPT_SoVITS/text/tone_sandhi.py:626
↓ 7 callersFunctionget_padding
(kernel_size, dilation=1)
GPT_SoVITS/BigVGAN/utils0.py:57
↓ 7 callersFunctionload_sovits_new
(sovits_path)
GPT_SoVITS/process_ckpt.py:129
↓ 7 callersFunctionmel_spectrogram
Calculate the mel spectrogram of an input signal. This function uses slaney norm for the librosa mel filterbank (using librosa.filters.mel) a
GPT_SoVITS/BigVGAN/meldataset.py:51
↓ 6 callersMethod__init__
(self, batch_size: int, vocab_size: int)
GPT_SoVITS/AR/models/t2s_model_cudagraph.py:30
↓ 6 callersMethod__setitem__
(self, key, value)
GPT_SoVITS/utils.py:346
↓ 6 callersFunction_numeric_feature_by_regex
(regex, s)
GPT_SoVITS/text/japanese.py:260
↓ 6 callersFunctioncheck_details
(path_list=None, is_train=False, is_dataset_processing=False)
tools/my_utils.py:90
↓ 6 callersFunctionclean_text
(text, language, version=None)
GPT_SoVITS/text/cleaner.py:21
↓ 6 callersFunctionget_padding
(kernel_size, dilation=1)
tools/AP_BWE_main/models/model.py:8
↓ 6 callersFunctionget_raw_t2s_model
(dict_s1)
GPT_SoVITS/export_torch_script.py:59
↓ 6 callersMethodremove_weight_norm
(self)
GPT_SoVITS/module/modules.py:209
↓ 6 callersMethodsave_configs
(self, configs_path: str = None)
GPT_SoVITS/TTS_infer_pack/TTS.py:377
↓ 6 callersFunctionscan_language_list
()
tools/i18n/i18n.py:14
↓ 6 callersFunctionverbalize_digit
(value_string: str, alt_one=False)
GPT_SoVITS/text/zh_normalization/num.py:309
↓ 5 callersMethod__init__
(self, t2s_path, vits_model)
GPT_SoVITS/onnx_export.py:87
↓ 5 callersFunctioncmb_spectrogram_to_wave
(spec_m, mp, extra_bins_h=None, extra_bins=None)
tools/uvr5/lib/lib_v5/spec_utils.py:327
↓ 5 callersMethodembedding
(self, index: int)
GPT_SoVITS/AR/modules/embedding.py:27
↓ 5 callersMethodget_2d_padding
( self, kernel_size: typing.Tuple[int, int], dilation: typing.Tuple[int, int] = (1, 1)
GPT_SoVITS/BigVGAN/discriminators.py:488
↓ 5 callersFunctionget_sovits_version_from_path_fast
(sovits_path)
GPT_SoVITS/process_ckpt.py:100
↓ 5 callersFunctionhtml_center
(text, label="p")
GPT_SoVITS/inference_webui.py:1193
↓ 5 callersMethodprefill
(self, x: Tensor, mask: Tensor, kv_cache: KVCacheNHD)
GPT_SoVITS/AR/models/t2s_model_cudagraph.py:163
↓ 5 callersMethodremove_weight_norm
(self)
GPT_SoVITS/BigVGAN/bigvgan.py:357
↓ 5 callersMethodset_device
To set the device for all models. Args: device: torch.device, the device to use for all models.
GPT_SoVITS/TTS_infer_pack/TTS.py:729
↓ 5 callersFunctionspec_to_mel_torch
(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
GPT_SoVITS/module/mel_processing.py:77
↓ 5 callersFunctionspectrogram_torch
( hann_window: Tensor, y: Tensor, n_fft: int, sampling_rate: int, hop_size: int, win_size: int, center: bo
GPT_SoVITS/export_torch_script.py:135
↓ 5 callersMethodto_mask
(self, x: torch.Tensor, padding_mask: Optional[torch.Tensor])
GPT_SoVITS/export_torch_script.py:238
↓ 5 callersMethodto_mask
( self, x: torch.Tensor, padding_mask: Optional[torch.Tensor], )
GPT_SoVITS/AR/models/t2s_model.py:122
↓ 5 callersFunctionverbalize_cardinal
(value_string: str)
GPT_SoVITS/text/zh_normalization/num.py:293
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_33966KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_537227KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_123812KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_123821KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_new.py:30
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
tools/uvr5/lib/lib_v5/layers_537238KB.py:53
↓ 4 callersMethod__init__
( self, normalized_shape: _shape_t, eps: float = 1e-5, elementwise_affine: boo
GPT_SoVITS/AR/modules/transformer_onnx.py:28
↓ 4 callersMethod__init__
( self, normalized_shape: _shape_t, eps: float = 1e-5, elementwise_affine: boo
GPT_SoVITS/AR/modules/transformer.py:28
↓ 4 callersMethod__init__
( self, in_channels, out_channels, filter_channels, kernel_size,
GPT_SoVITS/module/attentions_onnx.py:301
↓ 4 callersFunction_g2p
(segments)
GPT_SoVITS/text/chinese.py:94
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
GPT_SoVITS/eres2net/ERes2NetV2.py:207
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
GPT_SoVITS/eres2net/ERes2Net.py:206
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
GPT_SoVITS/eres2net/ERes2Net_huge.py:206
↓ 4 callersMethod_predict
(self, model_input: Dict[str, Any])
GPT_SoVITS/text/g2pw/onnx_api.py:286
↓ 4 callersFunction_time_num2str
A special case for verbalizing number in time.
GPT_SoVITS/text/zh_normalization/chronology.py:22
↓ 4 callersMethodaudio_postprocess
( self, audio: List[torch.Tensor], sr: int, batch_index_list: list = None,
GPT_SoVITS/TTS_infer_pack/TTS.py:1541
↓ 4 callersMethodbackward
(ctx, grad_output)
GPT_SoVITS/module/ddp_utils.py:44
↓ 4 callersMethodcompute_embedding3
(self, wav)
GPT_SoVITS/sv.py:24
↓ 4 callersFunctiondenorm_spec
(x)
GPT_SoVITS/export_torch_script_v3v4.py:217
↓ 4 callersMethodencode
(self, x)
GPT_SoVITS/module/core_vq.py:221
↓ 4 callersFunctionget_sovits_weights
(sovits_path)
GPT_SoVITS/export_torch_script_v3v4.py:586
↓ 4 callersFunctionget_spepc
(hps, filename, dtype, device, is_v2pro=False)
GPT_SoVITS/inference_webui.py:556
↓ 4 callersFunctionget_weights_names
()
config.py:86
↓ 4 callersMethodinfer_panel
( self, x: torch.LongTensor, #####全部文本token x_lens: torch.LongTensor, prompts
GPT_SoVITS/AR/models/t2s_model.py:966
↓ 4 callersMethodinference
Forward diffusion
GPT_SoVITS/module/models.py:1114
next →1–100 of 1,613, ranked by callers