MCPcopy Create free account

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

Functions1,532 in github.com/RVC-Boss/GPT-SoVITS

⨍ Functions 1,532◇ Types & classes 333↳ Endpoints 10
↓ 1 callersMethodinit_batch
(self)
GPT_SoVITS/AR/data/dataset.py:115
↓ 1 callersMethodinit_bert_weights
(self, base_path: str)
GPT_SoVITS/TTS_infer_pack/TTS.py:470
↓ 1 callersFunctioninit_bigvgan
()
GPT_SoVITS/export_torch_script_v3v4.py:498
↓ 1 callersMethodinit_cnhuhbert_weights
(self, base_path: str)
GPT_SoVITS/TTS_infer_pack/TTS.py:462
↓ 1 callersMethodinit_embed_
(self, data)
GPT_SoVITS/module/core_vq.py:140
↓ 1 callersFunctioninit_hifigan
()
GPT_SoVITS/export_torch_script_v3v4.py:515
↓ 1 callersMethodinit_onnx
(self)
GPT_SoVITS/AR/models/t2s_model_onnx.py:292
↓ 1 callersMethodinit_sr_model
(self)
GPT_SoVITS/TTS_infer_pack/TTS.py:651
↓ 1 callersMethodinit_sv_model
(self)
GPT_SoVITS/TTS_infer_pack/TTS.py:661
↓ 1 callersMethodinit_vocoder
(self, version: str)
GPT_SoVITS/TTS_infer_pack/TTS.py:592
↓ 1 callersMethodinitialize
(self, x, x_mask)
GPT_SoVITS/module/modules.py:831
↓ 1 callersFunctioninverse_mel_scale
(mel_freq: Tensor)
GPT_SoVITS/eres2net/kaldi.py:322
↓ 1 callersFunctionis_empty
(*items)
api.py:187
↓ 1 callersFunctionis_full
(*items)
api.py:194
↓ 1 callersFunctionjyuping_to_initials_finals_tones
(jyuping_syllables)
GPT_SoVITS/text/cantonese.py:118
↓ 1 callersFunctionkill_proc_tree
(pid, including_parent=True)
webui.py:215
↓ 1 callersFunctionkl_loss
z_p, logs_q: [b, h, t_t] m_p, logs_p: [b, h, t_t]
GPT_SoVITS/module/losses.py:45
↓ 1 callersFunctionkmeans
(samples, num_clusters: int, num_iters: int = 10)
GPT_SoVITS/module/core_vq.py:72
↓ 1 callersFunctionkorean_to_lazy_ipa
(text)
GPT_SoVITS/text/korean.py:280
↓ 1 callersFunctionlaplace_smoothing
(x, n_categories: int, epsilon: float = 1e-5)
GPT_SoVITS/module/core_vq.py:51
↓ 1 callersFunctionload_checkpoint
(filepath, device)
GPT_SoVITS/BigVGAN/inference_e2e.py:22
↓ 1 callersFunctionload_checkpoint
(filepath, device)
GPT_SoVITS/BigVGAN/tests/test_cuda_vs_torch_model.py:48
↓ 1 callersFunctionload_config
(config_path: os.PathLike, use_default: bool = False)
GPT_SoVITS/text/g2pw/utils.py:132
↓ 1 callersFunctionload_cudnn
()
tools/my_utils.py:140
↓ 1 callersFunctionload_data
(file_name: str = "./lib/name_params.json")
tools/uvr5/lib/utils.py:8
↓ 1 callersFunctionload_hparams_from_json
(path)
GPT_SoVITS/BigVGAN/bigvgan.py:25
↓ 1 callersFunctionload_language_list
(language)
tools/i18n/i18n.py:8
↓ 1 callersFunctionload_wav_to_torch
(full_path)
GPT_SoVITS/utils.py:178
↓ 1 callersFunctionload_yaml_config
(path)
GPT_SoVITS/AR/utils/io.py:7
↓ 1 callersFunctionlogits_to_probs
( logits, previous_tokens: Optional[torch.Tensor] = None, temperature: float = 1.0, top_k: Opt
GPT_SoVITS/export_torch_script.py:46
↓ 1 callersFunctionlogits_to_probs
( logits, previous_tokens=None, temperature: float = 1.0, top_k=None, top_p=None, repe
GPT_SoVITS/AR/models/t2s_model_onnx.py:26
↓ 1 callersFunctionlogits_to_probs
( logits, previous_tokens: Optional[torch.Tensor] = None, temperature: float = 1.0, top_k: Opt
GPT_SoVITS/AR/models/utils.py:147
↓ 1 callersFunctionlost_P
(y)
GPT_SoVITS/AR/models/utils.py:253
↓ 1 callersFunctionmain
()
tools/slicer2.py:155
↓ 1 callersFunctionmain
()
GPT_SoVITS/s2_train_v3.py:53
↓ 1 callersFunctionmain
()
GPT_SoVITS/export_torch_script.py:833
↓ 1 callersFunctionmain
()
GPT_SoVITS/s2_train_v3_lora.py:53
↓ 1 callersFunctionmain
()
GPT_SoVITS/inference_cli.py:53
↓ 1 callersFunctionmain
()
GPT_SoVITS/s2_train.py:53
↓ 1 callersFunctionmain
(args)
GPT_SoVITS/s1_train.py:85
↓ 1 callersFunctionmain
()
GPT_SoVITS/BigVGAN/train.py:611
↓ 1 callersFunctionmain
()
GPT_SoVITS/BigVGAN/inference_e2e.py:69
↓ 1 callersFunctionmain
()
GPT_SoVITS/BigVGAN/inference.py:54
↓ 1 callersMethodmake_buckets
(self, bucket_width: float = 2.0)
GPT_SoVITS/AR/data/bucket_sampler.py:83
↓ 1 callersFunctionmake_padding
(width, cropsize, offset)
tools/uvr5/lib/utils.py:15
↓ 1 callersFunctionmake_reject_y
(y_o, y_lens)
GPT_SoVITS/AR/models/utils.py:244
↓ 1 callersFunctionmerge_short_text_in_array
(texts, threshold)
GPT_SoVITS/inference_webui.py:696
↓ 1 callersFunctionmerge_short_text_in_array
(texts: str, threshold: int)
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py:34
↓ 1 callersFunctionmulti_head_attention_forward_patched
( query, key, value, embed_dim_to_check: int, num_heads: int, in_proj_weight,
GPT_SoVITS/AR/modules/patched_mha_with_cache_onnx.py:7
↓ 1 callersFunctionmultinomial_sample_one_no_sync
(probs_sort)
GPT_SoVITS/export_torch_script.py:84
↓ 1 callersFunctionmultinomial_sample_one_no_sync
( probs_sort, )
GPT_SoVITS/AR/models/t2s_model_onnx.py:74
↓ 1 callersFunctionmultinomial_sample_one_no_sync
( probs_sort, )
GPT_SoVITS/AR/models/utils.py:140
↓ 1 callersFunctionmy_save
(fea, path)
GPT_SoVITS/utils.py:67
↓ 1 callersFunctionmy_save
(fea, path)
GPT_SoVITS/prepare_datasets/2-get-sv.py:35
↓ 1 callersFunctionmy_save
(fea, path)
GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py:45
↓ 1 callersFunctionmy_save
(fea, path)
GPT_SoVITS/prepare_datasets/1-get-text.py:37
↓ 1 callersFunctionname2go
(wav_name, wav_path)
GPT_SoVITS/prepare_datasets/2-get-sv.py:82
↓ 1 callersFunctionname2go
(wav_name, lines)
GPT_SoVITS/prepare_datasets/3-get-semantic.py:89
↓ 1 callersFunctionnorm_spec
(x)
api.py:234
↓ 1 callersMethodnorm_spec
(self, x)
GPT_SoVITS/module/data_utils.py:353
↓ 1 callersMethodnorm_spec
(self, x)
GPT_SoVITS/module/data_utils.py:591
↓ 1 callersMethodnorm_spec
(self, x)
GPT_SoVITS/module/data_utils.py:802
↓ 1 callersMethodnormalize_sentence
(self, sentence: str)
GPT_SoVITS/text/zh_normalization/text_normlization.py:128
↓ 1 callersFunctiononly_asr
(input_file, language)
tools/asr/funasr_asr.py:15
↓ 1 callersFunctiononly_punc
(text)
api.py:694
↓ 1 callersFunctionpack_aac
(audio_bytes, data, rate)
api.py:631
↓ 1 callersFunctionpack_aac
(io_buffer: BytesIO, data: np.ndarray, rate: int)
api_v2.py:193
↓ 1 callersFunctionpack_ogg
(audio_bytes, data, rate)
api.py:567
↓ 1 callersFunctionpack_ogg
(io_buffer: BytesIO, data: np.ndarray, rate: int)
api_v2.py:176
↓ 1 callersFunctionpack_one
(t, pattern)
tools/uvr5/bs_roformer/bs_roformer.py:31
↓ 1 callersFunctionpack_one
(t, pattern)
tools/uvr5/bs_roformer/mel_band_roformer.py:34
↓ 1 callersFunctionpack_raw
(audio_bytes, data, rate)
api.py:613
↓ 1 callersFunctionpack_raw
(io_buffer: BytesIO, data: np.ndarray, rate: int)
api_v2.py:182
↓ 1 callersFunctionpack_wav
(audio_bytes, rate)
api.py:619
↓ 1 callersFunctionpack_wav
(io_buffer: BytesIO, data: np.ndarray, rate: int)
api_v2.py:187
↓ 1 callersMethodphonemize
(self, text: str, espeak: bool = False)
GPT_SoVITS/AR/text_processing/phonemizer.py:52
↓ 1 callersFunctionpiecewise_rational_quadratic_transform
( inputs, unnormalized_widths, unnormalized_heights, unnormalized_derivatives, inverse=Fal
GPT_SoVITS/module/transforms.py:12
↓ 1 callersFunctionplot_spectrogram_clipped
(spectrogram, clip_max=2.0)
GPT_SoVITS/BigVGAN/utils0.py:27
↓ 1 callersFunctionpost_replace_ph
(ph)
GPT_SoVITS/text/korean.py:301
↓ 1 callersFunctionpost_replace_ph
(ph)
GPT_SoVITS/text/japanese.py:119
↓ 1 callersFunctionpredict
(session, onnx_input: Dict[str, Any], labels: List[str])
GPT_SoVITS/text/g2pw/onnx_api.py:33
↓ 1 callersMethodprediction
(self, m, vocal_root, others_root, format)
tools/uvr5/mdxnet.py:172
↓ 1 callersFunctionprepare_onnx_input
( tokenizer, labels: List[str], char2phonemes: Dict[str, List[int]], chars: List[str], tex
GPT_SoVITS/text/g2pw/dataset.py:30
↓ 1 callersFunctionpreprocess
(X_spec)
tools/uvr5/lib/utils.py:54
↓ 1 callersMethodpreprocess
(self, text: str, lang: str, text_split_method: str, version: str = "v2")
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py:59
↓ 1 callersFunctionpreprocess_jap
Reference https://r9y9.github.io/ttslearn/latest/notebooks/ch10_Recipe-Tacotron.html
GPT_SoVITS/text/japanese.py:151
↓ 1 callersFunctionprocess
(data, res)
GPT_SoVITS/prepare_datasets/1-get-text.py:86
↓ 1 callersFunctionprocess_text
(texts)
GPT_SoVITS/inference_webui.py:1094
↓ 1 callersFunctionpyopenjtalk_g2p_prosody
Extract phoneme + prosoody symbol sequence from input full-context labels. The algorithm is based on `Prosodic features control by symbols as inp
GPT_SoVITS/text/japanese.py:183
↓ 1 callersMethodqryword
(self, o_word)
GPT_SoVITS/text/english.py:309
↓ 1 callersFunctionrand_gumbel
Sample from the Gumbel distribution, protect from overflows.
GPT_SoVITS/module/commons.py:35
↓ 1 callersFunctionrational_quadratic_spline
( inputs, unnormalized_widths, unnormalized_heights, unnormalized_derivatives, inverse=Fal
GPT_SoVITS/module/transforms.py:100
↓ 1 callersFunctionread_clean_buffer
(audio_bytes)
api.py:668
↓ 1 callersFunctionread_dict
()
GPT_SoVITS/text/g2pw/g2pw.py:128
↓ 1 callersFunctionread_dict_new
()
GPT_SoVITS/text/english.py:155
↓ 1 callersMethodrecovery_order
Recovery the order of the audio according to the batch_index_list. Args: data (List[list(torch.Tensor)]): the out of ord
GPT_SoVITS/TTS_infer_pack/TTS.py:943
↓ 1 callersFunctionreduce_vocal_aggressively
(X, y, softmask)
tools/uvr5/lib/lib_v5/spec_utils.py:139
↓ 1 callersFunctionreload_data
(index, batch)
tools/subfix_webui.py:37
↓ 1 callersMethodremove_weight_norm
(self)
GPT_SoVITS/module/attentions.py:443
↓ 1 callersFunctionrepeat_P
(y)
GPT_SoVITS/AR/models/utils.py:245
← previousnext →501–600 of 1,532, ranked by callers