many stock gpus being more powerful than the highest end google offers

also i want to talk to jeff kramer first if hes cool with the project in general

cuz hes a great guy

well we do encourage that

really lovely man

he starts talking about seaman at １１：００

anyway thanks for your time im gonna go back to working on the model

here's a thought, what if the seaman transcripts are just typed IN ALL CAPS instead of eq'd

is that genius or just purely ridiculous

it will do absolutely nothing

everything is automatically put into lowercase by the cleaners

i had read somewhere it treats uppercase stuff different

ah i see

huh maybe that's not that bad after all

just have to do it for ３００ files

certain programs can do stuff like this in bulk

also might want to throw in a normalizer

not just for these but for every file

Jut To Be Safe

ye it seems audacity can do it

yea

though be careful when using audacity to do bulk normalization

just selecting all then using normalizer will normalize to the peak of the loudest file rather than the peak of every individual track

it only seems to normalize properly as part of a macro

So do I necessarily need to get the creators plan to get ais accepted on the site

Shouldn't need to?

Oh thanks just wanted know cause I really wanna flood the singers rappers and musicians categories

my tacotron 2 model isnt working

Generating mels Generating Mels 100% 200/200 [00:04<00:00, 36.43it/s] Checking for missing files Checking Training Files [WARNING] wavs/1.wav.npy in filelist while expecting .npy . wavs/1.wav.npy|Normally I try to talk about games I've played before or at least have heard a bit about. [WARNING] does not exist. --------------------------------------------------------------------------- FileNotFoundError Traceback (most recent call last) in 9 get_ipython().system('sed -i -- 's,.wav|,.npy|,g' "{hparams.training_files}"; sed -i -- 's,.wav|,.npy|,g' "{hparams.validation_files}"') 10 ---> 11 check_dataset(hparams) 2 frames /usr/local/lib/python3.8/dist-packages/numpy/lib/npyio.py in load(file, mmap_mode, allow_pickle, fix_imports, encoding) 415 own_fid = False 416 else: --> 417 fid = stack.enter_context(open(os_fspath(file), "rb")) 418 own_fid = True 419 FileNotFoundError: [Errno 2] No such file or directory: 'wavs/1.wav.npy'