yl4579/StyleTTS

Issues

• MelSpectrogram() and unspecified sampling rate

  #74 opened 7 months ago by dsplog
  1

• Is there a first-stage pretrained model?

  #77 opened 3 months ago by cnint0627
  0

• can't import mask_from_lens from monotonic_align

  #76 opened 3 months ago by cnint0627
  0

• Inference exact time for each word

  #62 opened a year ago by enla51
  5

• amazing work,can it support that generate the phoneme delayed time sequence?

  #75 opened 4 months ago by CasonTsai
  0

• Voice Quality issue using Librispeech

  #73 opened 9 months ago by Anshu-Kumar-1
  0

• Marathi Support ?

  #72 opened 10 months ago by raushanagrawal
  0

• 多卡训练的问题

  #53 opened a year ago by bobo-paopao
  5

• Is the uv detector trained in the pretrained pitch detector?

  #71 opened 10 months ago by auspicious3000
  0

• Has anyone had this problem when converting to onnx?

  #70 opened 10 months ago by bobo-paopao
  0

• StyleTTS 2

  #68 opened 10 months ago by fakerybakery
  1

• S2S

  #69 opened 10 months ago by pawanhv
  1

• question

  #65 opened a year ago by magicse
  2

• Pre-training model sound quality issues

  #64 opened a year ago by gachaun
  5

• train on ESD

  #63 opened a year ago by bobo-paopao
  1

• Question: Fine tuning LibriTTS with StyleTTS

  #61 opened a year ago by Yahya-khodr
  5

• Any-to-any and emotion examples

  #36 opened a year ago by sleimanitani
  6

• The pronunciations of single words or short words is poor?

  #60 opened a year ago by GuangChen2016
  1

• Training Model with new Dataset

  #59 opened a year ago by Yahya-khodr
  0

• Training the model

  #58 opened a year ago by Yahya-khodr
  1

• what is the mean=-4 and std=4 meannig?

  #57 opened a year ago by skysbird
  1

• First stage alignment training failed when TMA_CEloss=True

  #56 opened a year ago by auspicious3000
  2

• style encoder inconsistency

  #55 opened a year ago by auspicious3000
  1

• batch size and number of epochs for large dataset

  #54 opened a year ago by auspicious3000
  1

• About train on Vietnamese Dataset

  #52 opened a year ago by christopherohit
  1

• Need help for training

  #50 opened a year ago by nhanhttrong
  5

• hi，如果使用v4000 单卡 训练LibriTTS数据集，显卡内存只有16G， batch_size只能设置为8，训练时常大概为多长呢？谢谢

  #51 opened a year ago by bobo-paopao
  1

• how to Inference

  #48 opened a year ago by luwentao1989
  1

• s2s loss 和mono loss在第一阶段的训练中一直为0

  #49 opened a year ago by bobo-paopao
  1

• Source of Hifigan checkpoints?

  #47 opened a year ago by kmn1024
  1

• pretrained model of stage 1

  #46 opened a year ago by nhanhttrong
  0

• Can you offer the loss log of style tts

  #45 opened a year ago by hdmjdp
  1

• asr phone dict different from this

  #44 opened a year ago by hdmjdp
  1

• about ASR model

  #43 opened a year ago by hdmjdp
  1

• error while running train_second.py (caused by size mismatch)

  #41 opened a year ago
  2

• Would you recommend changing the code in the inference notebook when running a PL-BERT finetuned model?

  #42 opened a year ago
  1

• Code for Emotional Speech Synthesis

  #40 opened a year ago by satani99
  1

• Questions about the Evaluations

  #39 opened a year ago by Zhongxu-Wang
  1

• running train_first.py raises error

  #37 opened a year ago
  3

• turns out your code doesn't join the read wav paths from train_list.txt file with the dataset path (the location of train_list.txt)

  #38 opened a year ago
  0

• Phoneme sequence padding

  #35 opened a year ago by WorkingJack
  3

• What's r1_reg loss?

  #33 opened a year ago by splinter21
  1

• Probleam about data processing

  #32 opened a year ago by Zhongxu-Wang
  1

• s2s loss become nan

  #26 opened a year ago by startreker-shzy
  2

• crashes during training

  #31 opened a year ago by ppisljar
  4

• Why don't use "attention_weight" in train_first.py ?

  #30 opened a year ago by dy2009
  1

• Why I can't use your mel to train HiFi-Gan Vocoder ?

  #29 opened a year ago by dy2009
  1

• f0_extractor ?

  #28 opened a year ago by dy2009
  0

• monotonic error

  #27 opened a year ago by zdj97
  1

• Trying to have the inference demo work - but no success

  #25 opened 2 years ago by olup
  3