MCPcopy Create free account

hub / github.com/FireRedTeam/FireRedTTS / functions

Functions342 in github.com/FireRedTeam/FireRedTTS

⨍ Functions 342◇ Types & classes 96
Methodforward
(self, x, g=None)
fireredtts/modules/semantic_tokenizer/semantic_tokenizer.py:487
Methodforward
(self, x, x_len, downsample=True)
fireredtts/modules/semantic_tokenizer/semantic_tokenizer.py:514
Methodforward
( self, inp, inp_len, enable_vq=True, update_codebook=True, return_pre_quant=False )
fireredtts/modules/semantic_tokenizer/semantic_tokenizer.py:575
Methodforward
Returns the output of the convolution. Arguments --------- x : torch.Tensor (batch, time, channel) input to convo
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:164
Methodforward
(self, input)
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:276
Methodforward
Returns the normalized input tensor. Arguments --------- x : torch.Tensor (batch, time, [channels]) input to norm
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:358
Methodforward
Returns the linear transformation of input tensor. Arguments --------- x : torch.Tensor Input to transform linear
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:431
Methodforward
(self, x)
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:491
Methodforward
(self, x)
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:550
Methodforward
(self, x, lengths=None)
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:598
Methodforward
Calculates mean and std for a batch (input tensor). Arguments --------- x : torch.Tensor Tensor of shape [N, C, L
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:655
Methodforward
(self, x, lengths=None)
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:778
Methodforward
Returns the embedding vector. Arguments --------- x : torch.Tensor Tensor of shape (batch, time, channel).
fireredtts/modules/semantic_tokenizer/ecapa_tdnn.py:895
Methodforward
(self, inp, length=None)
fireredtts/modules/semantic_tokenizer/audio.py:74
Methodforward
(self, inp, length=None, split=True, split_size=4)
fireredtts/modules/semantic_tokenizer/hubert.py:41
Methodforward
( self, semantic_token, prompt_semantic_token, prompt_acoustic_token, spk_gpt )
fireredtts/models/token2audio.py:24
Methodforward
( self, semantic_token, prompt_semantic_token, prompt_acoustic_token, spk_gpt )
fireredtts/models/token2audio.py:79
Methodget_generator
(self, fake_inputs, **hf_generate_kwargs)
fireredtts/modules/semantic_llm/llm_gpt2.py:599
Methodget_logits
( self, final_norm, first_inputs, first_head, speech_conditioning_inpu
fireredtts/modules/acoustic_llm/acoustic_llm.py:722
Functionget_mask_from_lengths
(lengths, max_len=None)
fireredtts/modules/semantic_tokenizer/semantic_tokenizer.py:38
Methodinference
(self, cond_latents, text_inputs, **hf_generate_kwargs)
fireredtts/modules/semantic_llm/llm_gpt2.py:490
Functioninit_weights
(m)
fireredtts/modules/acoustic_codec/bigcodec.py:31
Functioninit_weights
(m, mean=0.0, std=0.01)
fireredtts/modules/bigvgan/bigvgan.py:11
Functionis_digit
(text)
fireredtts/modules/text_normalizer/utils.py:112
Functionis_eng_and_digit
(char)
fireredtts/modules/text_normalizer/utils.py:100
Methodload_model
(self, flow_path, bigvgan_path)
fireredtts/models/token2audio.py:69
Functionnull_position_embeddings
(range, dim)
fireredtts/modules/acoustic_llm/acoustic_llm.py:71
Functionnull_position_embeddings
(range, dim)
fireredtts/modules/semantic_llm/llm_gpt2.py:286
Functionpad_for_conv1d
( x: torch.Tensor, kernel_size: int, stride: int, padding_total: int = 0 )
fireredtts/modules/acoustic_codec/bigcodec.py:69
Functionpad_for_conv1d
( x: torch.Tensor, kernel_size: int, stride: int, padding_total: int = 0 )
fireredtts/modules/semantic_tokenizer/semantic_tokenizer.py:95
Methodprepare_inputs_for_generation
(self, input_ids, past_key_values=None, **kwargs)
fireredtts/modules/semantic_llm/llm_gpt2.py:28
Methodprepare_inputs_for_generation
(self, input_ids, past_key_values=None, **kwargs)
fireredtts/modules/semantic_llm/llm_gpt2.py:164
Functionprotect_float
(text)
fireredtts/utils/spliter.py:120
Methodremove_weight_norm
(self)
fireredtts/modules/acoustic_codec/bigcodec.py:579
Methodremove_weight_norm
(self)
fireredtts/modules/bigvgan/bigvgan.py:147
Methodremove_weight_norm
(self)
fireredtts/modules/bigvgan/bigvgan.py:230
Functionspectral_de_normalize_torch
(magnitudes)
fireredtts/modules/semantic_tokenizer/audio.py:32
Functionsplit_text
(text, length)
fireredtts/utils/spliter.py:130
Methodstore_prefix_emb
(self, prefix_emb)
fireredtts/modules/semantic_llm/llm_gpt2.py:161
Methodsynthesize
audio synthesize Args: prompt_wav (_type_): _description_ prompt_text (_type_): _description_ text (_type
fireredtts/models/fireredtts.py:189
Functionuniform_init
(*shape: int)
fireredtts/modules/acoustic_codec/vector_quantization.py:32
Functionunprotect_float
(text)
fireredtts/utils/spliter.py:125
← previous301–342 of 342, ranked by callers