Validation data

[mboeni]

Quick question: where do I get / generate the validation data required (I'm using the LJSpeech set)?

If you can point to other/better training data with the corresponding validation data, also let me know please.

[seungwonpark]

I simply split the whole LJ data to 9:1 for train/val.

Seung-won Park Undergraduate Student Dept. of Physics and Astronomy & Computer Science Engineering Seoul National University yyyyy@snu.ac.kr | http://swpark.me

---

From: Michael Boeni notifications@github.com Sent: Saturday, December 14, 2019 1:10:27 PM To: seungwonpark/melgan melgan@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [seungwonpark/melgan] Validation data (#38)

Quick question: where do I get / generate the validation data required (I'm using the LJSpeech set)?

If you can point to other/better training data with the corresponding validation data, also let me know please.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/seungwonpark/melgan/issues/38?email_source=notifications&email_token=ADGGC5T3JOFNB65YUSMMZK3QYVDUHA5CNFSM4J24VERKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IAQWXPA, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ADGGC5UHHDVIQ3MCYVTPM7LQYVDUHANCNFSM4J24VERA.

[mboeni]

That was quick! Thanks, will do.

[mboeni]

Any idea on this issue:

` λ python trainer.py -c config/config.yaml -n InitialRun 2019-12-14 22:51:36,483 - INFO - Starting new training run. Validation loop: 0%| | 0/1552 [00:00<?, ?it/s]2019-12-14 22:51:36,492 - INFO - Exiting due to exception: 'getstate' Traceback (most recent call last): File "D:\dev\melgan\utils\train.py", line 60, in train validate(hp, args, model_g, model_d, valloader, writer, step) File "D:\dev\melgan\utils\validation.py", line 13, in validate for mel, audio in loader: File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\site-packages\tqdm_tqdm.py", line 1022, in iter for obj in iterable: File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 278, in iter return _MultiProcessingDataLoaderIter(self) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 682, in init w.start() File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 112, in start self._popen = self._Popen(self) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) KeyError: 'getstate'

mbo@zendo /d/dev/melgan (master) λ Traceback (most recent call last): File "", line 1, in File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "C:\Users\mbo\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 115, in _main self = reduction.pickle.load(from_parent) EOFError: Ran out of input

?`

[mboeni]

Also, if you have any example code for the audio generation, that would be appreciated :)

[wangqilun]

@seungwonpark @mboeni Have you solve this error? I encountered the same error.

[teamimx]

Nope, not yet...

[kookiny]

@seungwonpark Anyone knows what the problem was? or solved it?

[MckinstryJ]

@seungwonpark Its been awhile since the last comment but has anyone figured out this issue for LJSpeech? Adjusting the batch_size to 1 or 2^n didn't help.