begeekmyfriend/tacotron2

Issues

• 中文语音合成无法对齐

  #41 opened 3 years ago by cptbtptp2333
  0

• 中英文混合

  #40 opened 3 years ago by evelynyhc
  10

• 请教tacotron2与melgan结合的问题

  #39 opened 3 years ago by yannier912
  28

• 合成效果不佳

  #38 opened 4 years ago by huhanpan
  2

• About the multi_speaker implemention.

  #37 opened 4 years ago by LeoniusChen
  4

• How to train WaveRNN

  #36 opened 4 years ago by dr-jaieun
  2

• Question about WaveGlow

  #35 opened 4 years ago by leijue222
  1

• 多gpu训练问题

  #34 opened 4 years ago by yannier912
  1

• Solution about add more speakers midway.

  #33 opened 4 years ago by leijue222
  4

• Preparation before training.

  #30 opened 4 years ago by leijue222
  52

• Results of multi-speaker training

  #32 opened 4 years ago by Ranzige
  3

• Poor results from wavernn generation

  #24 opened 5 years ago by morphr5466
  10

• 如何训练标贝数据集？

  #4 opened 5 years ago by xinzheshen
  25

• tacotron2整合版本有什么特别之处？

  #29 opened 4 years ago by joan126
  1

• WaveRNN generated samples sound strange

  #26 opened 4 years ago by tugstugi
  16

• Multi-speaker sample wav (with wavernn vocoder)

  #1 opened 5 years ago by begeekmyfriend
  2

• `ref_level_db = 20` and ` min_level_db = -100` Where did these values come from?Statistics?

  #17 opened 5 years ago by WithoutDoubt
  10

• Tacotron 2 with tensorflow 2

  #23 opened 5 years ago by dathudeptrai
  1

• how can train multi-speaker?

  #3 opened 5 years ago by bellfive
  14

• about alignment

  #22 opened 5 years ago by MorganCZY
  14

• error when inference

  #20 opened 5 years ago by MorganCZY
  17

• no mel-spectrogram saved in preprocessing stage

  #21 opened 5 years ago by MorganCZY
  4

• how many data should i use to train this model？

  #19 opened 5 years ago by ArtemisZGL
  4

• 怎么做到实时的语音合成

  #13 opened 5 years ago by freecui
  13

• GPU memory

  #14 opened 5 years ago by freecui
  13

• segment a uttence

  #6 opened 5 years ago by freecui
  5

• not stable when training the model in the first epoch

  #9 opened 5 years ago by wenbozhangjs
  3

• 中文版本

  #10 opened 5 years ago by wangqiang624731186
  1

• 断句错误和噪音

  #12 opened 5 years ago by morphr5466
  20

• 文本中的英文缩写转换语音

  #18 opened 5 years ago by jamesMuWB
  4

• 声音有点抖，有点沙哑

  #11 opened 5 years ago by freecui
  6

• requirements.txt

  #15 opened 5 years ago by agonzalezd
  6

• how to improve tts result

  #7 opened 5 years ago by freecui
  9

• audio preprocessing for wavernn

  #8 opened 5 years ago by violet-duck
  4

• Questions about training time

  #5 opened 5 years ago by xw1324832579
  4

• Pretrained model

  #2 opened 5 years ago by nmfisher
  7