every one of them

even the ones that process the dataset and train other stuff?

Yeah

I had this idea in my head that if I used these other training cells it would reset the HiFi GAN training steps

I'm a newbie at this lol

ok it's working, tysm can't wait to train my model up to 3100 epochs

Someone Test This Model https://drive.google.com/file/d/17Uw_Os2Ysb0VMVmZeXeuV_O9NMLLnUmW/view?usp=sharing

This Sounds Perfect

FileNotFoundError Traceback (most recent call last) in 115 116 # Convert to JSON --> 117 generate_json("trainfiles.txt", "trainfiles.json") 118 generate_json("valfiles.txt", "valfiles.json") 119 generate_json("allfiles.txt", "allfiles.json") in generate_json(inpath, outpath) 45 lpath = "wavs/" + lpath 46 size = os.stat( ---> 47 os.path.join(os.path.dirname(inpath), lpath) 48 ).st_size 49 x = { FileNotFoundError: [Errno 2] No such file or directory: 'wavs/1.wav'

it could use a bit more training probably, what's the dataset?

Hi. I'm brand new to doing these Talknet voices. I completely logistically understand how the are supposed to function and what I'm meant to do except for one thing. When training a talknet model there is a thing called Validation or something. It is a text file I think. I've also got my dataset, and the transcriptions for that.

My main question is what exacly IS the validation thinger

And what do I do to make one and what do I do with it

No need to make one. Just use the transcript.txt file.

So I copy paste the transcription file and rename it something else?

That's it?

IOHHH

I understand it just validates it's the right file

I've been being dumdum ok thanks

"ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. tensorflow 2.4.1 requires numpy~=1.19.2, but you have numpy 1.21.6 which is incompatible."

Got it after doing part 5

of the training notebook

Is that bad? It looks like I can just go on.

Nevermind I tried too go on but step 5 stops me from doing it saying the following

--------------------------------------------------------------------------- Exception Traceback (most recent call last) in 82 get_ipython().system('tar -xf "{dataset}"') 83 else: ---> 84 raise Exception("Unknown extension for dataset") 85 if os.path.exists("/content/wavs/wavs"): 86 shutil.move("/content/wavs/wavs", "/content/tempwavs") Exception: Unknown extension for dataset

I never wrote any places or paths like that

halp plz

il wait

Pretty sure this means you put something other than a zip file in the dataset spot

I did.