huawei-noah/Speech-Backbones

Issues

• Montreal Forced Alignment (MFA) Version Inquiry

  #39 opened 2 months ago by zeynabyousefi
  3

• Not able to generate audio using libritts of as good quality as using ljspeech

  #23 opened 2 years ago by Hertin
  11

• Different Implementation of Diffusion Model

  #35 opened a year ago by siyag12
  1

• Generated Samples are noisy

  #37 opened 8 months ago by SandyPanda-MLDL
  1

• Two questions about DiffVC

  #31 opened a year ago by huangf79
  1

• mels_mode generation

  #36 opened 10 months ago by Biyani404198
  1

• Model training question

  #26 opened 2 years ago by Cpgrach
  5

• DOESN'T WORK

  #38 opened 5 months ago by yukiarimo
  1

• A bug in model/tts.py

  #28 opened 2 years ago by chep0k
  1

• Not possible to build

  #33 opened a year ago by asusdisciple
  1

• GradTTS device compatibility

  #34 opened a year ago by bukhalmae145
  0

• support for bigvgan

  #27 opened 2 years ago by eschmidbauer
  2

• about diffVC on Mandarin datasets

  #24 opened 2 years ago by Theweekfoolish229
  4

• Why does the BNE-PPG-VC model in your demo perform better than the pre-trained model given in the original paper?

  #20 opened 2 years ago by jiazj-jiazj
  1

• Finetuning a Grad-TTS model on a small dataset?

  #21 opened 2 years ago by godspirit00
  2

• About the prior loss and MAS algorithm

  #18 opened 2 years ago by cantabile-kwok
  2

• Multi-GPU training and expected epochs

  #9 opened 3 years ago by bieltura
  5

• Fine-tuning / Transfer Learning

  #8 opened 3 years ago by williamluer
  11

• Typo in some equations in GradTTS paper

  #25 opened 2 years ago by cantabile-kwok
  4

• Possibly missing __dict__ in the Projector class' constructor

  #17 opened 3 years ago by Sri-Harsha
  0

• How is `out_size` in `params` determined

  #16 opened 3 years ago by cantabile-kwok
  2

• Attention layer in GradTTS

  #15 opened 3 years ago by patrickvonplaten
  2

• ASR finetune ?

  #11 opened 3 years ago by Enescigdem
  1

• About end2end implementation

  #12 opened 3 years ago by quangnh-2761
  10

• Generated outputs sound robotic in some cases!

  #14 opened 3 years ago by aniketp02
  3

• Diffusion loss not decreasing

  #13 opened 3 years ago by aniketp02
  1

• Clipping distortion of the generated waveform

  #7 opened 3 years ago by WelkinYang
  3

• Grad-TTS in multispeaker setting

  #5 opened 3 years ago by ajinkyakulkarni14
  2

• [Errno 13] Permission denied: '/home/user/app/Grad-TTS/model/monotonic_align/core.c'

  #4 opened 3 years ago by AK391
  0

• Grad-TTS: Colab Notebook

  #2 opened 3 years ago by AK391
  2