Functions — github.com/MuBai-He/ChatWaifu-marai

CodeHub MCPcopy Create free account

hub / github.com/MuBai-He/ChatWaifu-marai / functions

Functions180 in github.com/MuBai-He/ChatWaifu-marai

⨍ Functions 180◇ Types & classes 29

↓ 10 callersFunctionget_label_value

(text, label, default, warning_name='value')

ChatWaifu_marai.py:107

↓ 8 callersMethod__init__

(self, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=0, p_dropout=0)

↓ 8 callersFunctionget_padding

(kernel_size, dilation=1)

↓ 6 callersMethod__init__

(self, initial_channel, resblock, resblock_kernel_sizes, resblock_dilation_sizes, upsample_rates, upsample_ini

↓ 6 callersMethodkeys

↓ 5 callersMethod__init__

(self, num_label_embeddings: int = 100, mask: bool = True)

hubert_model.py:11

↓ 4 callersFunctionchinese_to_bopomofo

text/mandarin.py:247

↓ 4 callersFunctionjapanese_to_romaji_with_accent

Reference https://r9y9.github.io/ttslearn/latest/notebooks/ch10_Recipe-Tacotron.html

text/japanese.py:74

↓ 4 callersFunctionlatin_to_bopomofo

text/mandarin.py:264

↓ 4 callersFunctionnumber_to_chinese

text/mandarin.py:240

↓ 3 callersMethod__init__

(self, in_channels, out_channels, filter_channels, kernel_size, p_dropout=0., activation=None, causal=False)

attentions.py:255

↓ 3 callersMethodencode

( self, x: torch.Tensor, layer: Optional[int] = None )

hubert_model.py:37

↓ 3 callersFunctionenglish_to_ipa

text/english.py:160

↓ 3 callersFunctionget_speaker_id

ChatWaifu_marai.py:97

↓ 3 callersMethodinfer

(self, x, x_lengths, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None, emotion_embeddin

↓ 3 callersFunctionvoice_conversion

ChatWaifu_marai.py:165

↓ 2 callersMethod_get_relative_embeddings

(self, relative_embeddings, length)

attentions.py:196

↓ 2 callersFunctionchinese_to_lazy_ipa

text/mandarin.py:301

↓ 2 callersFunctionchinese_to_romaji

text/mandarin.py:288

↓ 2 callersFunctionenglish_to_ipa2

text/english.py:176

↓ 2 callersFunctiongenerateSound

(inputString,language)

ChatWaifu_marai.py:129

↓ 2 callersFunctionget_label

ChatWaifu_marai.py:121

↓ 2 callersFunctionget_real_hatsuon

text/japanese.py:121

↓ 2 callersFunctionget_real_sokuon

text/japanese.py:115

↓ 2 callersFunctionget_text

(text, hps, cleaned=False)

ChatWaifu_marai.py:69

↓ 2 callersFunctionhangul_number

Reference https://github.com/Kyubyong/g2pK

text/korean.py:102

↓ 2 callersMethoditems

↓ 2 callersFunctionjapanese_to_ipa

text/japanese.py:127

↓ 2 callersFunctionjapanese_to_ipa2

text/japanese.py:138

↓ 2 callersFunctionkorean_to_ipa

text/korean.py:208

↓ 2 callersFunctionkorean_to_lazy_ipa

text/korean.py:199

↓ 2 callersFunctionlatin_to_hangul

text/korean.py:89

↓ 2 callersFunctionnumber_to_hangul

Reference https://github.com/Kyubyong/g2pK

text/korean.py:181

↓ 2 callersFunctionsearchsorted

(bin_locations, inputs, eps=1e-6)

transforms.py:47

↓ 2 callersFunctionshanghainese_to_ipa

text/shanghainese.py:54

↓ 2 callersFunctionspectral_normalize_torch

mel_processing.py:26

↓ 2 callersFunctiontext_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 c

text/__init__.py:5

↓ 1 callersMethod_absolute_position_to_relative_position

x: [b, h, l, l] ret: [b, h, l, 2*l-1]

attentions.py:228

↓ 1 callersMethod_attention_bias_proximal

Bias for self-attention to encourage attention to close positions. Args: length: an integer scalar. Returns: a Tensor with shape [

attentions.py:242

↓ 1 callersFunction_clean_text

(text, cleaner_names)

text/__init__.py:26

↓ 1 callersFunction_compute_mask

( shape: Tuple[int, int], mask_prob: float, mask_length: int, device: torch.device, min_ma

hubert_model.py:154

↓ 1 callersMethod_matmul_with_relative_keys

x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]

attentions.py:187

↓ 1 callersMethod_matmul_with_relative_values

x: [b, h, l, m] y: [h or 1, m, d] ret: [b, h, l, d]

attentions.py:178

↓ 1 callersFunction_number_to_shanghainese

text/shanghainese.py:39

↓ 1 callersMethod_relative_position_to_absolute_position

x: [b, h, l, 2*l-1] ret: [b, h, l, l]

attentions.py:211

↓ 1 callersMethodattention

(self, query, key, value, mask=None)

attentions.py:145

↓ 1 callersFunctionbopomofo_to_ipa

text/mandarin.py:276

↓ 1 callersFunctionbopomofo_to_ipa2

text/mandarin.py:282

↓ 1 callersFunctionbopomofo_to_romaji

text/mandarin.py:270

↓ 1 callersFunctioncantonese_to_ipa

text/cantonese.py:49

↓ 1 callersFunctionchinese_to_ipa

text/mandarin.py:308

↓ 1 callersFunctionchinese_to_ipa2

text/mandarin.py:321

↓ 1 callersFunctioncollapse_whitespace

text/english.py:94

↓ 1 callersFunctionconvert_pad_shape

↓ 1 callersFunctiondevanagari_to_ipa

text/sanskrit.py:52

↓ 1 callersFunctiondivide_hangul

text/korean.py:95

↓ 1 callersFunctiondynamic_range_compression_torch

PARAMS ------ C: compression factor

mel_processing.py:8

↓ 1 callersFunctiondynamic_range_decompression_torch

PARAMS ------ C: compression factor used to compress

mel_processing.py:17

↓ 1 callersFunctionenglish_to_lazy_ipa

text/english.py:169

↓ 1 callersFunctionenglish_to_lazy_ipa2

text/english.py:184

↓ 1 callersFunctionex_print

(text, escape=False)

ChatWaifu_marai.py:62

↓ 1 callersFunctionexpand_abbreviations

text/english.py:88

↓ 1 callersFunctionget_token

ChatWaifu_marai.py:43

↓ 1 callersFunctionhubert_soft

r"""HuBERT-Soft from `"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion"`. Args: path (str): path of a pretrai

hubert_model.py:209

↓ 1 callersFunctionjapanese_cleaners

text/cleaners.py:4

↓ 1 callersFunctionjapanese_to_ipa3

text/japanese.py:147

↓ 1 callersFunctionlatin_to_ipa

text/cantonese.py:43

↓ 1 callersFunctionlatin_to_ipa

text/shanghainese.py:48

↓ 1 callersFunctionlatin_to_thai

text/thai.py:41

↓ 1 callersMethodlogits

(self, x: torch.Tensor)

hubert_model.py:48

↓ 1 callersFunctionmark_dark_l

text/english.py:156

↓ 1 callersMethodmask

(self, x: torch.Tensor)

hubert_model.py:30

↓ 1 callersFunctionngu_dialect_to_ipa

(text, dialect)

text/ngu_dialect.py:21

↓ 1 callersFunctionnormalize_numbers

text/english.py:146

↓ 1 callersFunctionnum_to_thai

text/thai.py:38

↓ 1 callersFunctionnumber_to_cantonese

text/cantonese.py:39

↓ 1 callersFunctionnumber_to_shanghainese

text/shanghainese.py:44

↓ 1 callersFunctionpiecewise_rational_quadratic_transform

(inputs, unnormalized_widths,

transforms.py:12

↓ 1 callersFunctionprint_speakers

(speakers, escape=False)

ChatWaifu_marai.py:89

↓ 1 callersFunctionrational_quadratic_spline

(inputs, unnormalized_widths, unnormalized_heights

transforms.py:96

↓ 1 callersFunctionsequence_mask

(length, max_length=None)

↓ 1 callersFunctionslice_segments

(x, ids_str, segment_size=4)

↓ 1 callersFunctionspectrogram_torch

(y, n_fft, sampling_rate, hop_size, win_size, center=False)

mel_processing.py:40

↓ 1 callersFunctionsymbols_to_japanese

text/japanese.py:68

↓ 1 callersMethodunits

(self, wav: torch.Tensor)

hubert_model.py:68

↓ 1 callersMethodvalues

↓ 1 callersMethodvoice_conversion

(self, y, y_lengths, sid_src, sid_tgt)

Method__contains__

Method__getitem__

(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., window_size=4, **kwar

attentions.py:11

(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., proximal_bias=False,

attentions.py:48

(self, channels, out_channels, n_heads, p_dropout=0., window_size=None, heads_share=True, block_length=None, p

attentions.py:99

(self, **kwargs)

(self, in_channels, filter_channels, kernel_size, p_dropout, n_flows=4, gin_channels=0)

(self, in_channels, filter_channels, kernel_size, p_dropout, gin_channels=0)

(self, n_vocab, out_channels, hidden_channels, filter_channels, n_heads, n

(self, channels, hidden_channels, kernel_size, dilation_rate, n_layers, n_

(self, in_channels, out_channels, hidden_channels, kernel_size, dilation_rate,

(self, n_vocab, spec_channels, segment_size, inter_channels, hidden_channels, filter_

(self, channels, eps=1e-5)

next →1–100 of 180, ranked by callers