kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
Jupyter NotebookMIT
Issues
- 2
The learning rate decreases after a specific epoch.
#425 opened by Cyp9715 - 0
Config yaml files for Parallel WaveGAN are identical for both normal and long setting?
#426 opened by PussyCat0700 - 0
Streaming Vocoder?
#422 opened by Kit-Bower-Morris - 3
How can I solve "UnicodeDecodeError" ?
#421 opened by omoidegit - 1
code error in path "parallel_wavegan/bin/decode.py"
#419 opened by ZXHY-82 - 2
Upload latest release to PyPI
#417 opened by tjysdsg - 2
Question when use apex
#416 opened by South-Twilight - 1
Discriminator checkpoints?
#415 opened by kmn1024 - 3
- 1
The generated output contains a lot of noise.
#410 opened by Lanzik - 1
- 2
make apex
#406 opened by Blakey-Gavin - 1
out of memory when inference
#408 opened by xiaolongwu0713 - 2
How to select num_taps and beta for PQMF?
#404 opened by bfs18 - 0
apex
#405 opened by Blakey-Gavin - 2
Questions on SVS
#399 opened by Askropios - 1
illegal line count -- -2
#401 opened by noanymore - 4
The program crashed during training
#400 opened by zzxiang - 1
Analysis or paper of hubert-discrete-hifigan?
#392 opened by seastar105 - 2
How would you train for BW extension?
#397 opened by kelseyjd - 1
Refactor Conv1d's `padding` with `same`
#395 opened by tarepan - 1
Train a HIFIGan
#393 opened by yijingshihenxiule - 0
- 1
- 1
Question about config
#383 opened by Kio829 - 0
how to convert model to torchscript?
#382 opened by zhuziying - 0
Neural Homomorphic Vocoder
#381 opened by wizardk - 1
How to continue network training
#380 opened by nellorebhanuteja - 1
job failed unsure why
#379 opened by luxzia - 17
training time for HiFiGAN LJSpeech
#377 opened by nellorebhanuteja - 1
aishell3 ckpt
#378 opened by 1nlplearner - 1
Train hifigan using 44.1K audio file
#376 opened by gandolfxu - 2
Low inference speed of TTS on GPU
#375 opened by dalvlv - 13
Upload trained vocoder to huggingface
#358 opened by roholazandie - 0
Avocodo Discriminators
#374 opened by Flux9665 - 3
stylemelagn model structure change for 32Khz vocoder
#370 opened by wblgers - 0
- 1
kaldiio loading flac failed
#372 opened by Jackiexiao - 1
tensorboard graphs
#371 opened by nellorebhanuteja - 1
- 2
Stylemelgan G + HifiGan D -- error on step 1
#368 opened by skol101 - 2
How to decode with the same results.
#365 opened by winddori2002 - 1
- 6
How to modify the distributed in config.yml?
#360 opened by Hu-chengyang - 12
How to modify the sampling rate when use csmsc dataset to train the vocoder?
#359 opened by Hu-chengyang - 4
How to solve the problem local/data_prep.sh: line 59: nkf: command not found?
#357 opened by Hu-chengyang - 2
How to solve the problems?
#356 opened by Hu-chengyang - 1
how to use apex to parallel-training
#355 opened by c9412600 - 4
Train libriTTS problem
#353 opened by winddori2002 - 1
How to train Hifi-GAN in new dataset
#352 opened by majidAdibian77