search

jjery2243542 / voice_conversion

246 stars 67 forks source link

The code in solver.py seems wrong. #20

Closed poor1017 closed 4 years ago

poor1017 commented 4 years ago

Hi @jjery2243542 

Thank you for your code. When I read the code, I find there is something wrong:

For master branch:

No 'train' mode in function 'solver.Solver.train', but in main.py, I see the code 'solver.train(args.output_model_path, args.flag, mode='train')'.

Please have a check if you have time.

josearangos commented 4 years ago

Hello,

Dear friend I want to speak with you about this repository, so that together we can run this experiment. could you please give me your email. My email is: jose.arangos@udea.edu.co

Do you know how I can solve the Error in self.permute_data (data)?

I was trying to run the main.py file to retrain the model as you guided but in the middle of the process it threw an error "too many values to unpack (expected 2)" at line 279 in solver.py which is (c_i, c_j), (x_i_t, x_i_tk, x_i_prime, x_j) = self.permute_data(data). Then I recognized that permute() function does not output many elements like this.

Did I miss something? Can anybody help me out of it?

josearangos commented 4 years ago

this repository did not work but this one did

https://github.com/arshd91/multitarget-voice-conversion-vctk

poor1017 commented 4 years ago

Hi @josearangos

Actually, you can use the 'public' branch and you will get the pretty good results for English without any errors.