CjangCjengh/MoeGoe

Issues

• 请问以.npy结尾的情感参考文件该如何生成？

  #32 opened 2 years ago by yz1392946854
  3

• TypeError: type object got multiple values for keyword argument 'n_speakers'

  #39 opened 2 years ago by Anomyous1
  6

• RuntimeError: Error(s) in loading state_dict for SynthesizerTrn

  #35 opened 2 years ago by QFDG
  3

• 导入模型和配置文件之后报错

  #44 opened 2 years ago by tago233
  3

• moegoe gui無法使用vits_chinese專案内的模型

  #53 opened a year ago by Amazon90
  1

• 情感reference会导致错误的停顿

  #57 opened a year ago by ben-8878
  0

• Choose language with multilingual model made with VITS-fast-fine-tuning repo

  #56 opened a year ago by DogeLord081
  0

• AttributeError: 'SynthesizerTrn' object has no attribute 'emb_g'

  #40 opened 2 years ago by doxtor6
  3

• Exception: jieba: file does not exist: C:\jieba\dict.txt

  #14 opened a year ago by Kashouryo
  4

• What tool did you use to create the voice model?

  #55 opened a year ago by kbuwel
  0

• 是否支持汉语方言训练呢？

  #12 opened 2 years ago by Ecauchy
  2

• TypeError: models.SynthesizerTrn() got multiple values for keyword argument 'n_speakers'

  #46 opened 2 years ago by kotoriiiii
  2

• 请问这个语音合成算法能否使用gpu来运算

  #50 opened 2 years ago by focusaibuilder
  1

• Required to update numpy version dependency

  #52 opened a year ago by RyaoChengfeng
  1

• Default is CPU calculation or GPU calculation

  #51 opened 2 years ago by YJ-KER
  0

• 如何解决未定义问题

  #48 opened 2 years ago by ElainaOwla
  0

• Is there a manual?

  #22 opened 2 years ago by JAME-CMD
  1

• where is MoeGoe.exe? Do you mean MoeGoe.py?

  #26 opened 2 years ago by JJun-Guo
  2

• moegoe GUI 广东方言[GD][GD] 保存音频后播放没有声音。

  #41 opened 2 years ago by kirbystudy
  0

• 是否可以编辑生成wav文件的参数

  #43 opened 2 years ago by OrangesFlower
  1

• data.pkl and config.json how convert to model.pth file?

  #42 opened 2 years ago by erikaemma
  0

• question about to build exe

  #38 opened 2 years ago by zwluoqi
  0

• 用提供的与训练模型合成的语音只有吸气声

  #34 opened 2 years ago by jacksong18
  4

• opencc.OpenCC('zaonhe')

  #33 opened 2 years ago by DuQingChen
  3

• question on VC

  #37 opened 2 years ago by EmasikWothlan
  0

• 我遇到了报错

  #36 opened 2 years ago by C9H20sx
  0

• RuntimeError: Error(s) in loading state_dict for SynthesizerTrn:size mismatch for enc_p.emb.weight: copying a param with shape torch.Size([43, 192]) from checkpoint, the shape in current model is torch.Size([40, 192]).

  #28 opened 2 years ago by perfsakuya
  4

• 韩语数据集相关问题

  #18 opened 2 years ago by ORI-Muchim
  0

• 运行一段时间后会出现的错误，重装后过一段时间仍会出现

  #30 opened 2 years ago by vgngtvb
  0

• 无法运行指令

  #29 opened 2 years ago by Triffinf
  1

• 我尝试使用nodejs的child_process.spawn().stdin.write(text)向其输入日文时出现了错误

  #27 opened 2 years ago by zwa73
  1

• 请问什么时候能开放下载模型呢？

  #25 opened 2 years ago by gyy0814
  0

• Japanese phonemes issue?

  #24 opened 2 years ago by Norgus
  6

• sensei

  #23 opened 2 years ago by mario824914x
  0

• Project dependencies may have API risk issues

  #19 opened 2 years ago by PyDeps
  1

• About the problem that the pyinstaller package contains torch

  #17 opened 2 years ago by rdp-studio
  1

• Empty output when using the Chinese model

  #15 opened 2 years ago by Kashouryo
  1

• VITS Japanese模型训练报错

  #10 opened 2 years ago by QuellaMC
  4

• Problem occurred when using official hubert-soft model

  #13 opened 2 years ago by wind4000
  0

• 按照视频设置无法输出语音

  #11 opened 2 years ago by ffftian
  0

• 请问大佬有尝试过 tacotron2，fastspeech2 等模型的效果吗？

  #3 opened 2 years ago by sixyang
  3