NVIDIA/waveglow

Issues

• ModuleNotFoundError: No module named 'layers'

  #281 opened 2 months ago by xinxinye000
  1

• none of the synthesized speech has sound

  #280 opened 5 months ago by Mrwyl
  0

• Error : waveglow and pad_center() takes 1 positional argument but 2 were given on Denoiser

  #279 opened 8 months ago by catafest
  0

• WaveGlow: a Flow-based Generative Network for Speech Synthesis

  #278 opened a year ago by adlinjukesha
  0

• The training log shows that the loss value is negative

  #251 opened 4 years ago by AugggRush
  2

• ERROR: No matching distribution found for torch==1.0

  #274 opened 2 years ago by ghostlyghastly
  2

• Can't install matplotlib

  #275 opened 2 years ago by ghostlyghastly
  0

• Need help warm start model

  #273 opened 2 years ago by gb-ey
  1

• why "audio = audio.astype('int16')" is uesd ?

  #271 opened 2 years ago by wsywsywsywsywsy979
  6

• GPU required or CPU compatible?

  #255 opened 3 years ago by lkurlandski
  1

• how to make a list of the file names to use for training/testing?

  #270 opened 2 years ago by ZHUBAJIEJIU
  1

• Training different 'n_mel_channels' models

  #264 opened 2 years ago by anitaweng
  2

• Document Compatible Python Versions

  #253 opened 3 years ago by kevinjdolan
  1

• spectrogram (image)-to-to wav

  #269 opened 2 years ago by ahmeftah
  0

• Continue Training from a checkpoint saved in checkpoints folder

  #267 opened 2 years ago by pgovil1998
  1

• An important issue on multispeaker inference

  #266 opened 2 years ago by hongchengzhu
  0

• Multispeaker trained model inferencing different voices

  #260 opened 3 years ago by BakuDev
  1

• How to generate an audio with this model?? after i train with my model what do i do to generate an audio with a text i want?

  #229 opened 4 years ago by aurbina198
  6

• Converting audio samples to mel then back to audio just generates noise.

  #262 opened 3 years ago by jamescasia
  3

• Convert log Mel bank energy to audio by your model

  #263 opened 3 years ago by zuujhyt
  0

• waveglow training error

  #228 opened 4 years ago by mataym
  3

• Can not load model

  #261 opened 3 years ago by yasntrk
  1

• Is it possible to split denoiser module?

  #259 opened 3 years ago by EuphoriaCelestial
  0

• I want to run a trained "yolov5s.pt" in a local pc for a usage of a opencv application .How can I do that in simples as a newbies to pytorch

  #258 opened 3 years ago by Hasintha-Hewage
  0

• Waveglow Pretrained Model shall i use for male voice to do transfer learning? Need guidance

  #257 opened 3 years ago by MuruganR96
  0

• tts_waveglow_268m from_pretrained KeyError

  #256 opened 3 years ago by markwny
  0

• pose = list(self.allPose.keys())[list(self.allPose.values()).index(pose_ind)] ValueError: 'PD+00' is not in list

  #254 opened 3 years ago by soufiene-fst
  0

• RuntimeError: A tensor was not contiguous.

  #248 opened 4 years ago by sciai-ai
  2

• Waveglow broken audio

  #252 opened 4 years ago by CrazyPlaysHD
  0

• 16kHz Pre-Trained model

  #232 opened 4 years ago by xDuck
  1

• What is the size of waveglow

  #250 opened 4 years ago by Johnzxf
  0

• 4 whistling frequencies

  #249 opened 4 years ago by innarid
  3

• Python 3.8/Torch 1.6 'Conv1d' object has no attribute '_non_persistent_buffers_set'

  #235 opened 4 years ago by jonaskohler
  4

• Electric sound

  #246 opened 4 years ago by innarid
  2

• How to specify graphics card in training

  #247 opened 4 years ago by DDeng-Z
  0

• At 140k of wavelow training, the sound spectrum produced is as follows. The sound noise is serious

  #227 opened 4 years ago by Text2-m
  1

• Issue training for male dataset

  #245 opened 4 years ago by zshakeri
  1

• Waveglow as Inverse STFT function

  #244 opened 4 years ago by ajinkyakulkarni14
  2

• denoised-output write error

  #243 opened 4 years ago by leonvit
  0

• WaveGlow MelAudioLoader Question

  #242 opened 4 years ago by dxlin17
  0

• Expect the `waveglow_old.pt` model file

  #241 opened 4 years ago by X-CCS
  0

• Different sampling rate model inference speed abnormal

  #240 opened 4 years ago by lightwithshadow
  0

• Why do we have randomness when inferring?

  #239 opened 4 years ago by OriYitzhaki
  0

• Can I generate a waveform that resembles the voice of an existing sample?

  #238 opened 4 years ago by shamoons
  0

• Code getting stuck

  #236 opened 4 years ago by ry85
  1

• How to infer waveform from mel spectrams already generated with same hop length,win length,sample rate?

  #237 opened 4 years ago by IrisLhy
  0

• Is the published model trained only on LJSpeech?

  #234 opened 4 years ago by MuyangDu
  2

• what is the mel-spectrogram parameters of the pretrain model?

  #230 opened 4 years ago by zlfengyi
  2

• evaluate a model

  #233 opened 4 years ago by cyh-ustc
  0

• About the caculate of logdet

  #231 opened 4 years ago by gzfffff
  1