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
↓ 2 callersFunctionconvert_pad_shape
(pad_shape)
GPT_SoVITS/module/commons.py:106
↓ 2 callersFunctioncreate_model
(language="zh", **kwargs)
tools/asr/funasr_asr.py:24
↓ 2 callersFunctioncut_text
(text, punc)
api.py:791
↓ 2 callersMethoddecode_next_token
(self, x: torch.Tensor, k_cache: torch.Tensor, v_cache: torch.Tensor)
GPT_SoVITS/export_torch_script.py:281
↓ 2 callersFunctiondefault
(v, d)
tools/uvr5/bs_roformer/bs_roformer.py:27
↓ 2 callersFunctiondefault
(v, d)
tools/uvr5/bs_roformer/mel_band_roformer.py:30
↓ 2 callersFunctiondenorm_spec
(x)
GPT_SoVITS/TTS_infer_pack/TTS.py:63
↓ 2 callersMethoddequantize
(self, embed_ind)
GPT_SoVITS/module/core_vq.py:217
↓ 2 callersFunctiondiscriminator_loss
( disc_real_outputs: List[torch.Tensor], disc_generated_outputs: List[torch.Tensor] )
GPT_SoVITS/BigVGAN/loss.py:212
↓ 2 callersFunctionexists
(val)
tools/uvr5/bs_roformer/attend.py:7
↓ 2 callersMethodexport
(self, ref_seq, text_seq, ref_bert, text_bert, ssl_content, project_name, dynamo=False)
GPT_SoVITS/onnx_export.py:132
↓ 2 callersFunctionexport_bert
(output_path)
GPT_SoVITS/export_torch_script.py:602
↓ 2 callersMethodextend_pe
Reset the positional encodings.
GPT_SoVITS/AR/modules/embedding.py:54
↓ 2 callersMethodextract_latent
(self, ssl_content)
GPT_SoVITS/stream_v2pro.py:177
↓ 2 callersFunctionfeature_loss
(fmap_r: List[List[torch.Tensor]], fmap_g: List[List[torch.Tensor]])
GPT_SoVITS/BigVGAN/loss.py:203
↓ 2 callersFunctionfft_hp_filter
(spec, bin_start, bin_stop)
tools/uvr5/lib/lib_v5/spec_utils.py:410
↓ 2 callersFunctionfind_best_audio_offset_fast
(reference_audio: Tensor, search_audio: Tensor)
GPT_SoVITS/stream_v2pro.py:188
↓ 2 callersFunctionfix_g2pk2_error
(text)
GPT_SoVITS/text/korean.py:155
↓ 2 callersMethodforward
(self, x)
tools/uvr5/lib/lib_v5/nets_new.py:70
↓ 2 callersMethodforward
(self, x)
GPT_SoVITS/export_torch_script.py:197
↓ 2 callersMethodforward3
(self, x)
GPT_SoVITS/eres2net/ERes2Net.py:239
↓ 2 callersFunctionfull_cjk
(text)
GPT_SoVITS/text/LangSegmenter/langsegmenter.py:22
↓ 2 callersFunctiongenerator_loss
( disc_outputs: List[torch.Tensor], )
GPT_SoVITS/BigVGAN/loss.py:228
↓ 2 callersMethodget_bert_feature
(self, text: str, word2ph: list)
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py:191
↓ 2 callersFunctionget_file_md5
(file_path)
GPT_SoVITS/text/g2pw/g2pw.py:20
↓ 2 callersFunctionget_hash
(fp: str)
GPT_SoVITS/text/japanese.py:50
↓ 2 callersFunctionget_method
(name: str)
GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py:8
↓ 2 callersFunctionget_model
(hps)
GPT_SoVITS/s2_train_v3_lora.py:152
↓ 2 callersFunctionget_models
()
tools/asr/config.py:1
↓ 2 callersFunctionget_optim
(net_g)
GPT_SoVITS/s2_train_v3_lora.py:160
↓ 2 callersFunctionget_phones_and_bert
(text, language, version, final=False)
api.py:545
↓ 2 callersFunctionget_timing_signal_1d
(length, channels, min_timescale=1.0, max_timescale=1.0e4)
GPT_SoVITS/module/commons.py:65
↓ 2 callersFunctionget_tts_wav
( ref_wav_path, prompt_text, prompt_language, text, text_language, how_to_cut=i1
GPT_SoVITS/inference_webui.py:790
↓ 2 callersFunctionhandle
( refer_wav_path, prompt_text, prompt_language, text, text_language, cut_punc,
api.py:1100
↓ 2 callersFunctionhandle_change
(path, text, language)
api.py:1079
↓ 2 callersFunctionhandle_control
(command)
api.py:1071
↓ 2 callersFunctionhangul_number
Reference https://github.com/Kyubyong/g2pK
GPT_SoVITS/text/korean.py:183
↓ 2 callersMethodinfer
(self, ssl, y, y_lengths, text, text_lengths, test=None, noise_scale=0.5)
GPT_SoVITS/module/models.py:973
↓ 2 callersMethodinfer_panel_naive
( self, x: torch.LongTensor, #####全部文本token x_lens: torch.LongTensor, prompts
GPT_SoVITS/AR/models/t2s_model.py:816
↓ 2 callersFunctioninference
data : dic configs
tools/uvr5/lib/utils.py:25
↓ 2 callersFunctioninit_bigvgan
()
api.py:237
↓ 2 callersFunctioninit_bigvgan
()
GPT_SoVITS/inference_webui.py:479
↓ 2 callersFunctioninit_hifigan
()
api.py:255
↓ 2 callersFunctioninit_hifigan
()
GPT_SoVITS/inference_webui.py:498
↓ 2 callersFunctioninit_sv_cn
()
api.py:285
↓ 2 callersFunctioninit_sv_cn
()
GPT_SoVITS/inference_webui.py:530
↓ 2 callersMethodis_ready
(self)
api.py:183
↓ 2 callersFunctionkaiser_sinc_filter1d
(cutoff, half_width, kernel_size)
GPT_SoVITS/BigVGAN/alias_free_activation/torch/filter.py:30
↓ 2 callersMethodmake_input_data
(self, x, x_lens, y, y_lens, bert_feature)
GPT_SoVITS/AR/models/t2s_model.py:355
↓ 2 callersFunctionmake_pad_mask
Args: lengths: A 1-D tensor containing sentence lengths. max_len: The length of masks. Returns: Return a 2-
GPT_SoVITS/AR/models/utils.py:16
↓ 2 callersFunctionmake_padding
(width, cropsize, offset)
tools/uvr5/lib/lib_v5/dataset.py:104
↓ 2 callersFunctionmel_scale
(freq: Tensor)
GPT_SoVITS/eres2net/kaldi.py:330
↓ 2 callersFunctionmel_scale_scalar
(freq: float)
GPT_SoVITS/eres2net/kaldi.py:326
↓ 2 callersMethodmel_spectrogram
Mirrors AudioSignal.mel_spectrogram used by BigVGAN-v2 training from: https://github.com/descriptinc/audiotools/blob/master/audiotool
GPT_SoVITS/BigVGAN/loss.py:107
↓ 2 callersFunctionmodel2cuda
(net_g, rank)
GPT_SoVITS/s2_train_v3_lora.py:168
↓ 2 callersFunctionmy_save
(fea, path)
GPT_SoVITS/process_ckpt.py:12
↓ 2 callersFunctionmy_save2
(fea, path, model_version)
GPT_SoVITS/process_ckpt.py:30
↓ 2 callersFunctionname2go
(wav_name, wav_path)
GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py:78
↓ 2 callersFunctionnorm_spec
(x)
GPT_SoVITS/TTS_infer_pack/TTS.py:59
↓ 2 callersFunctionnumber_to_hangul
Reference https://github.com/Kyubyong/g2pK
GPT_SoVITS/text/korean.py:262
↓ 2 callersFunctionpack_audio
(audio_bytes, data, rate)
api.py:670
↓ 2 callersFunctionpack_audio
(io_buffer: BytesIO, data: np.ndarray, rate: int, media_type: str)
api_v2.py:268
↓ 2 callersMethodpad_y_eos
(self, y, y_mask_int, eos_id)
GPT_SoVITS/AR/models/t2s_model.py:578
↓ 2 callersFunctionphone2str
(phone_string: str, mobile=True)
GPT_SoVITS/text/zh_normalization/phonecode.py:31
↓ 2 callersMethodpostprocess_emb
(self, embed_ind, shape)
GPT_SoVITS/module/core_vq.py:214
↓ 2 callersMethodpre_infer
( self, prompts: LongTensor, ref_seq: LongTensor, text_seq: LongTensor,
GPT_SoVITS/stream_v2pro.py:21
↓ 2 callersMethodpre_merge_for_modify
(self, seg: List[Tuple[str, str]])
GPT_SoVITS/text/tone_sandhi.py:750
↓ 2 callersMethodpre_seg_text
(self, text: str, lang: str, text_split_method: str)
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py:77
↓ 2 callersMethodpredict
(self, x_mag, aggressiveness=None)
tools/uvr5/lib/lib_v5/nets.py:114
↓ 2 callersMethodpreprocess
(self, x)
GPT_SoVITS/module/core_vq.py:204
↓ 2 callersMethodquantize
(self, x)
GPT_SoVITS/module/core_vq.py:208
↓ 2 callersFunctionsample
( logits, previous_tokens: Optional[torch.Tensor] = None, **sampling_kwargs, )
GPT_SoVITS/AR/models/utils.py:192
↓ 2 callersFunctionsave_audio
(audio, path, sr)
GPT_SoVITS/BigVGAN/utils0.py:95
↓ 2 callersFunctionsave_checkpoint
(filepath, obj)
GPT_SoVITS/BigVGAN/utils0.py:69
↓ 2 callersFunctionscan_checkpoint
(cp_dir, prefix, renamed_file=None)
GPT_SoVITS/BigVGAN/utils0.py:75
↓ 2 callersFunctionsearchsorted
(bin_locations, inputs, eps=1e-6)
GPT_SoVITS/module/transforms.py:45
↓ 2 callersFunctionsequence_mask
(length, max_length=None)
GPT_SoVITS/module/commons.py:117
↓ 2 callersFunctionset_default
()
webui.py:104
↓ 2 callersMethodset_ref_audio
To set the reference audio for the TTS model, including the prompt_semantic and refer_spepc. Args: ref_audio_
GPT_SoVITS/TTS_infer_pack/TTS.py:751
↓ 2 callersMethodslice
(self, waveform)
tools/slicer2.py:67
↓ 2 callersMethodsola_algorithm
( self, audio_fragments: List[torch.Tensor], overlap_len: int, search_len:int=
GPT_SoVITS/TTS_infer_pack/TTS.py:1783
↓ 2 callersFunctionspectral_normalize_torch
(magnitudes)
GPT_SoVITS/module/mel_processing.py:26
↓ 2 callersFunctionsplit
(todo_text)
GPT_SoVITS/inference_webui.py:1075
↓ 2 callersFunctionsplit
(todo_text)
GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py:70
↓ 2 callersFunctionsplit_jako
(tag_lang,item)
GPT_SoVITS/text/LangSegmenter/langsegmenter.py:48
↓ 2 callersFunctionstft_mag
(audio, n_fft=2048, hop_length=512)
tools/AP_BWE_main/models/model.py:449
↓ 2 callersFunctiontext_normalize
(text)
GPT_SoVITS/text/english.py:233
↓ 2 callersMethodto_batch
( self, data: list, prompt_data: dict = None, batch_size: int = 5, thr
GPT_SoVITS/TTS_infer_pack/TTS.py:856
↓ 2 callersFunctiontrain_and_evaluate
( rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger,
GPT_SoVITS/s2_train_v3.py:275
↓ 2 callersFunctiontrain_and_evaluate
(rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger, writers)
GPT_SoVITS/s2_train_v3_lora.py:263
↓ 2 callersFunctiontrain_and_evaluate
(rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger, writers)
GPT_SoVITS/s2_train.py:318
↓ 2 callersMethodtraining_step
(self, batch: Dict, batch_idx: int)
GPT_SoVITS/AR/models/t2s_lightning_module.py:42
↓ 2 callersFunctiontts_handle
Text to speech handler. Args: req (dict): { "text": "", # str.(required) text to be sy
api_v2.py:345
↓ 2 callersMethodupdate_version
(self, version: str)
GPT_SoVITS/TTS_infer_pack/TTS.py:399
↓ 2 callersMethodvalidation_step
(self, batch: Dict, batch_idx: int)
GPT_SoVITS/AR/models/t2s_lightning_module.py:83
↓ 2 callersFunctionweight_norm_modules
(module, name="weight", dim=0)
GPT_SoVITS/module/attentions.py:499
↓ 1 callersFunctionMLP
(dim_in, dim_out, dim_hidden=None, depth=1, activation=nn.Tanh)
tools/uvr5/bs_roformer/bs_roformer.py:216
↓ 1 callersFunctionMLP
(dim_in, dim_out, dim_hidden=None, depth=1, activation=nn.Tanh)
tools/uvr5/bs_roformer/mel_band_roformer.py:225
↓ 1 callersMethod__init__
(self, max_sec, t2s_model)
api.py:468
↓ 1 callersMethod__init__
(self, args)
tools/uvr5/mdxnet.py:75
← previousnext →201–300 of 1,613, ranked by callers