Issues
- 0
Block on preprocessing
#78 opened by zhang-yunke - 0
hello world text
#77 opened by captainsan - 1
TBPTTIter.split_length() error
#75 opened by hash2430 - 0
- 0
- 0
Look like it fails on '!' character.
#73 opened by mrgloom - 7
ERROR: Failed to find norm file.
#69 opened by mrgloom - 1
Understanding feat tensor dimensions
#72 opened by mrgloom - 0
How this repo compared to Merlin?
#71 opened by mrgloom - 0
ImportError: No module named torch
#70 opened by mrgloom - 0
bash scripts/download_tools.sh failed on Mac OS
#68 opened by mrgloom - 12
Parameters for dataset in the wild
#58 opened by aomv - 0
Train VCTK dataset for all speakers
#66 opened by SibtainRazaJamali - 0
Error when 'make' HTK-3.4.1 and hts_core.
#65 opened by hatiff - 1
Error running train.py
#63 opened by sharonzhou - 1
No matching distribution found for phonemizer (from -r scripts/requirements.txt (line 5))
#61 opened by ethanjyx - 7
Any clue? Missing norm_info_mgc_lf0_vuv_bap_63_MVN.dat while prepossessing Lj Speech Dataset.
#48 opened by niravpatel2008 - 1
- 1
- 0
Using pre-trained model for new speaker?
#60 opened by xerdink - 1
Trump voice
#54 opened by aomv - 1
Out of memory in validation step
#57 opened by sausax - 2
- 47
How much minutes of audio datasets to train for a single speaker using blizzard model?
#28 opened by jaxlinksync - 0
Recreating blizzard baseline
#55 opened by ghostcow - 0
accuracy of the model by using vctk
#53 opened by vinaykumarbundla - 3
Training Error. Epoch 5.
#50 opened by PetrochukM - 1
visualize flag not working with visdom
#52 opened by ghostcow - 2
What does a good loss curve look like?
#51 opened by PetrochukM - 1
How much hours or minutes of training data do we need to make the performance very good?
#45 opened by jaxlinksync - 7
- 1
How to train the samples obtained from public?too much noise and speed too fast!
#37 opened by lvenoxi - 1
- 1
Full VCTK dataset
#47 opened by PetrochukM - 6
Blizzard Model
#44 opened by PetrochukM - 1
From English into Chinese?
#38 opened by ChrisChan2013 - 2
espeak or espeak-NG?
#43 opened by PetrochukM - 1
- 9
Reproducing the results
#41 opened by pfriesch - 2
Error during training
#39 opened by jaxlinksync - 1
Confusion of the Phoneme Generation
#42 opened by darongliu - 2
What is the split ratio between the training set and test set of the VCTK data provided in your project?
#32 opened by jaxlinksync - 1
Training on big dataset.
#35 opened by hepower - 1
Can loop support parallel training in multiple GPU?
#34 opened by hepower - 2
- 1
- 2
- 1
Error when synthesis wave with the download model.
#31 opened by hepower - 0
Does anyone successfully train a multi-speaker loop model with his/her own data?
#29 opened by hepower - 1
Training Epochs Number
#27 opened by gaziway