Issues
- 1
- 1
- 0
Section 4.4 End-to-End Speech Synthesis
#169 opened by freedomtowin - 5
python environment
#149 opened by simonwindtner - 0
Library Issue
#168 opened by avdg-dev - 2
- 4
Hardcoded num_mels to 80?
#166 opened by bzp83 - 0
Obvious harmonics appear in the generated wavs
#165 opened by Ziyi6 - 3
Mel spectrogram npy contents
#134 opened by leandro-gracia-gil - 2
MelDataset mel VS mel_loss
#163 opened by nikifori - 2
output of inference.py seems to have high sample rate
#138 opened by Pked01 - 1
- 0
- 0
For Ready-to-use req.txt for training. (Create new txt file and paste this text, Required python 3.8)
#155 opened by iamshreeji-copy2 - 0
How to fine tune hifi-gan with transformer.
#161 opened by imrankh46 - 0
d_loss nonconvergence?
#160 opened by a897456 - 4
Pretrained Hifi GAN vocoder at 16KHz
#125 opened by narendranp - 0
Choice and effect of "segment size"
#159 opened by BenjSta - 1
aliasing artifact, how to fix it?
#137 opened by splinter21 - 0
License of pre-trained models
#157 opened by geliAI - 0
DiscriminatorP(2)/P(3)...P(11)
#154 opened by a897456 - 0
kernel_size=3?
#152 opened by a897456 - 0
Generate mel-spectrograms in numpy format using Tacotron2 with teacher-forcing.
#151 opened by a897456 - 0
Can I get the mel_spectrogram through the librosa.feature.melspectrogram instead of the Tacotron2
#150 opened by a897456 - 0
- 1
Why we need to finetune on Tacotron output?
#147 opened by JiachuanDENG - 2
Spectrogram (image)-to-wav
#127 opened by ahmeftah - 0
init_weights has no effect after weight_norm
#145 opened by Andras7 - 0
How to improve HiFi-GAN output mel spectrogram
#144 opened by schnekk - 0
learning loss explosion
#143 opened by ikpark09 - 0
- 0
How to convert the genererator files into .pth format and generate the config file that can be used with tts
#142 opened by arnav-newzera - 0
Pre-trained Discriminator model
#136 opened by compressor1212 - 0
what about this config in 16k
#140 opened by weituotian - 2
the training Mel must be 80 channels? I use the other shape, it has no error ,but inference
#139 opened by lunar333 - 0
Teacher-Forcing How To
#135 opened by SuperJonotron - 1
- 2
TypeError: guvectorize() missing 1 required positional argument: 'signature'
#131 opened by baipeng0110 - 3
How to improve HiFi-GAN in stream TTS applications?
#132 opened by JohnHerry - 0
Tacotron + HIFI GAN Fine tuned: Sounds distorted.
#130 opened by Mixomo - 0
no end audio(slice audio) has poor effect
#129 opened by yyjjww - 0
Train/test split used for VCTK data
#128 opened by spun-oliver - 0
LJSpeech-1.1/wavs/-0113.wav not found
#126 opened by kienld3049 - 2
pickle.UnpicklingError: invalid load key, '{'
#123 opened by rafa6g - 0
how to generated mel-spectrogram?
#124 opened by Deerzh - 0
about mel spec extract
#122 opened by zxj329 - 0
Output Spectrum has no information from 4k to 11k by using pretrained model (generator_v3)
#121 opened by yugeshav - 3
Pause between sentence
#120 opened by chikiuso - 1
how to use pretrained models?
#119 opened by yasntrk - 0
pre-trained model - universal model in v2?
#118 opened by dsplog