ming024/FastSpeech2

Issues

• ModuleNotFoundError: No module named 'distutils.msvccompiler'

  #236 opened 2 months ago by bvajk
  0

• Self-Attention Mask Expansion Issue

  #235 opened 2 months ago by fanoprcs
  0

• CUDA out of memory

  #233 opened 6 months ago by gaoyiyao
  1

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

  #234 opened 4 months ago by CasonTsai
  0

• How to train with Indian Accent

  #227 opened 8 months ago by Jainu-s
  2

• How do I align my data

  #208 opened a year ago by hkeliang
  2

• how to slove indexSelectSmallIndex: block: [1,0,0], thread: [32,0,0] Assertion `srcIndex < srcSelectDimSize` failed when training ASILLE3

  #220 opened a year ago by foolishcqx
  1

• train.yaml

  #232 opened 6 months ago by gaoyiyao
  0

• train/py

  #231 opened 6 months ago by gaoyiyao
  0

• preprocess.py

  #230 opened 6 months ago by gaoyiyao
  0

• FileNotFoundError: [Errno 2] No such file or directory: '/root/FastSpeech2-master/preprocessed_data/LJSpeech/mel/LJSpeech-mel-LJ016-0364.npy'

  #229 opened 6 months ago by gaoyiyao
  0

• data

  #228 opened 6 months ago by gaoyiyao
  0

• Multi-language support in one sentence

  #207 opened a year ago by shirubei
  1

• MFA version

  #225 opened 7 months ago by shreeshailgan
  4

• Unused character embeddings?

  #209 opened a year ago by g-milis
  4

• Fluctuating training loss

  #206 opened a year ago by 299792459b
  2

• Discrepancy in the Number of Decoder Layers

  #226 opened 8 months ago by shreeshailgan
  0

• [CONTRIBUTION] Speech Dataset Generator

  #224 opened 9 months ago by davidmartinrius
  0

• ran out of input

  #223 opened 9 months ago by ariameetgit
  0

• How do you train the mfa acoustic model?

  #198 opened 2 years ago by SandroChen
  1

• not found modules

  #222 opened a year ago by yumoqing
  0

• Minor bug in loading vocoders

  #221 opened a year ago by Mahyar24
  0

• About fine-tuning issues.

  #199 opened a year ago by ltydd
  4

• Duration of synthesis output is very short

  #219 opened a year ago by hplanmuc
  0

• The numbers of the audio samples and speakers mismatch of LibriTTS dataset

  #218 opened a year ago by shiyanpei0826
  0

• ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 96 from C header, got 80 from PyObject

  #210 opened a year ago by WJHBLUESAPPHIRE
  2

• 求救！！在VarianceAdaptor中 进行pith_embeding的时候显示编码器输出张量x和音素嵌入张量形状不同无法相加

  #216 opened a year ago by aaqq112
  0

• Inconvergence in pitch and energy loss

  #213 opened a year ago by zhoufqing
  0

• fine-tuning issue

  #212 opened a year ago by zhoufqing
  1

• there is an error scipy 1.5.0 while import

  #211 opened a year ago by hevenangel
  0

• synthesize.py LibriTTS RuntimeError: CUDA error: device-side assert triggered

  #190 opened 2 years ago by Bingtai1015
  1

• RuntimeError: The size of tensor a (33) must match the size of tensor b (36) at non-singleton dimension 1

  #204 opened a year ago by ltydd
  1

• aishell3处理：使用mfa官方dict和声学模型处理aishell3

  #188 opened 2 years ago by tuntun990606
  16

• 1

  #205 opened a year ago by sunnnnnnnny
  0

• RuntimeError: Error(s) in loading state_dict for FastSpeech2

  #202 opened a year ago by fangg2000
  1

• e_control not used during synthesis

  #200 opened a year ago by lordzuko
  0

• FastSpeech 2s

  #197 opened 2 years ago by izzajalandoni
  0

• model cantnot fit to data, and test voice is too bad when i use the paper configuration

  #193 opened 2 years ago by hhm853610070
  3

• Pretained model link is invalid

  #196 opened 2 years ago by Nueve879
  0

• Frequency of LibriTTS data. 24000 or 22050?

  #195 opened 2 years ago by Zhongxu-Wang
  0

• Should we rely on tensorboard's output for duraion, pitch and energy?

  #194 opened 2 years ago by aidosRepoint
  0

• What should I do if I want to use phonemes and words to generate sentences at the same time?

  #191 opened 2 years ago by tuntun990606
  0

• How about adding a discriminator to the Fastspeech2 to improve the naturalness of the spectrum？

  #189 opened 2 years ago by Bingtai1015
  0

• synthesize chinese sentences

  #178 opened 2 years ago by dayi1233
  1

• A custom text for inference

  #187 opened 2 years ago by WGook
  0

• The duration.npy file is picking zero as duration value for the phones with short duration in textgrids

  #185 opened 2 years ago by nayanjha16
  0

• How would I train a TTS model on music? So instead of it talking from a prompt, it makes music from a prompt.

  #183 opened 2 years ago by breadbrowser
  0

• [nltk_data] Error loading averaged_perceptron_tagger: <urlopen error

  #181 opened 2 years ago by lunar333
  0

• the last words of my synthesized voice are often unclea

  #180 opened 2 years ago by tuntun990606
  0

• FastSpeechs training error

  #179 opened 2 years ago by lunar333
  0