CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
51.65k stars 8.66k forks source link

No matter how much I replace the *.pt files with those of the Spanish language. It download english files *.pt (encoder, sinthesizer and vocoder) #1203

Open fran478 opened 1 year ago

fran478 commented 1 year ago

Hello, When I run the demo . It tells me all the tests they were passed. Then it asks me for the location of an mp3 file to be cloned. When I give you the location

Testing the vocoder... All test passed! You can now synthesize speech.

enc_model_fpath: saved_models\default\encoder.pt syn_model_fpath: synthesizer\saved_models\cvcorpus\cvcorpus_200k.pt voc_model_fpath: saved_models\default\vocoder.pt cpu: False no_sound: False seed: None

Then it asks me for the location of a voice mp3 file to be cloned. When I give you the location. I know the file exists, but it still says the following

Interactive generation loop Reference voice: enter an audio filepath of a voice to be cloned (mp3, wav, m4a, flac, ...): C:\1.mp3 C:\Users\ewr\anaconda3\envs\sintetizador-espanol\lib\site-packages\librosa\core\audio.py:165: UserWarning: PySoundFile failed. Trying audioread instead. warnings.warn("PySoundFile failed. Trying audioread instead.") Caught exception: FileNotFoundError(2, 'No such file or directory') Restarting

when i run python demo_toolbox.py

It runs with the configuration in English and I can only select within of the software encoder,vocoder,sinthesizer as default. Arguments: datasets_root: None models_dir: saved_models cpu: False seed: None

If I change the trainings inside the saved_models folder for the encoder, vocoder, sinthesizer in Spanish. When I run python demo_toolbox.py. the encoder, vocoder, sinthesizer training is downloaded in English. I don't know what I'm doing wrong. Thank you

goge-sudo commented 10 months ago

我也一样,按提示找到了,ui.py里的280行,像是设置自己的路径出现问题,在demo_toolbox.py的20行,但是我不理解程序的语法,能告诉我:你的解决方法吗