search

Mangio621 / Mangio-RVC-Fork

*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.
MIT License
1.04k stars 220 forks source link

Training not working stopping after one epooch #107

Open ozmix opened 1 year ago

ozmix commented 1 year ago

Hi all I was using the previous one before this with easy GUI, and it worked.

I figured out how to allow easy GUI to work again thanks to the issues pages here to fix it

However now every time I use training this comes up after the first epoch

I am honestly not sure how to deal with it, this only happens with easy GUI too I can train just fine on go bat web

any ideas ?

Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 108, in run File "F:\RVC\Mangio-RVC-v23.7.0\train_nsf_sim_cache_sid_load_pretrain.py", line 225, in run train_and_evaluate( File "F:\RVC\Mangio-RVC-v23.7.0\train_nsf_sim_cache_sid_load_pretrain.py", line 579, in train_and_evaluate cursor.execute("SELECT stop FROM stop_train LIMIT 1") sqlite3.OperationalError: no such table: stop_train

Skyf1re commented 1 year ago

Hello! Try pasting these after "cursor = conn.corsor()" which on the 358 line:

cursor.execute('''
      CREATE TABLE IF NOT EXISTS stop_train (
        stop BOOL
      )
    ''')

    conn.commit()

It worked for me

Aemeth21 commented 1 year ago

I had the same problem. I managed to fix it downloading and replacing 'train_nsf_sim_cache_sid_load_pretrain.py' file for the updated one. You can download the file here: https://github.com/Mangio621/Mangio-RVC-Fork/blob/main/train_nsf_sim_cache_sid_load_pretrain.py. The file you need to replace is found on the main Mangio RVC folder. Hope that helps :D