deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove unnecessary code

Browse Source
This commit is contained in:
lyuxiang.lx
2024-09-05 14:26:12 +08:00
parent 11eacb810e
commit e141634da1
2 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
cosyvoice/flow/flow.py
View File

@@ -113,7 +113,7 @@ class MaskedDiffWithXvec(torch.nn.Module):
# concat text and prompt_text # concat text and prompt_text
token_len1, token_len2 = prompt_token.shape[1], token.shape[1] token_len1, token_len2 = prompt_token.shape[1], token.shape[1]
token, token_len = torch.concat([prompt_token, token], dim=1), prompt_token_len + token_len token, token_len = torch.concat([prompt_token, token], dim=1), prompt_token_len + token_len
mask = (~make_pad_mask(token_len)).to(embedding.dtype).unsqueeze(-1).to(embedding) mask = (~make_pad_mask(token_len)).unsqueeze(-1).to(embedding)
token = self.input_embedding(torch.clamp(token, min=0)) * mask token = self.input_embedding(torch.clamp(token, min=0)) * mask
# text encode # text encode

2
cosyvoice/flow/flow_matching.py
View File

@@ -14,8 +14,6 @@
import torch import torch
import torch.nn.functional as F import torch.nn.functional as F
from matcha.models.components.flow_matching import BASECFM from matcha.models.components.flow_matching import BASECFM
import onnxruntime as ort
import numpy as np
class ConditionalCFM(BASECFM): class ConditionalCFM(BASECFM):
def __init__(self, in_channels, cfm_params, n_spks=1, spk_emb_dim=64, estimator: torch.nn.Module = None): def __init__(self, in_channels, cfm_params, n_spks=1, spk_emb_dim=64, estimator: torch.nn.Module = None):