José Vicente Egas López

I actually found out why. It is due to the shape of my MFCCs. The shape I have is (1, 40, 498). In your case, it is (1, 40, 282)....

@bagustris was thinking about the same. But seems like he splits the data and makes 20% for test. In my case, I have `train_dataset`, validation (`dev_dataset`), and evaluation (`test_dataset`). At...

where exactly in the code? I am also interested in that. Or you mean directly remove from the csv files?

I have tried the following: `ki = io.xopen('../final.dubm', mode='r') # opening the dubm` `FullGmm.read(ki.stream(), ki.binary) # reading the dubm` However, this will result in an error since I am inputting...

Thanks for your reply, @kamo-naoyuki . Yes, I meant loading them into a numpy, I intend to use the models generated for a specific experiment in computational paralinguistics. Now I...

Thank you so much, @kamo-naoyuki. I will try this out and see. :)

> @ljc222 @Ha0Tang if you go through past issues, you'll stumble across this repo/notebook which puzzles it all together to make it work end-to-end: https://github.com/KnurpsBram/AutoVC_WavenetVocoder_GriffinLim_experiments/blob/master/AutoVC_WavenetVocoder_GriffinLim_experiments_17jun2020.ipynb @lisabecker hi! How do you...

Sure, that worked. Thanks for your reply. I've seen there's also a `Libri1Mix` corpus. How does one generate this one? or ir corresponds to the mix_single folders (1 speaker)?

Try with ``` feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name) ```

Near 200k iterations and I couldn't get rid of the 'robotized' voice. Somebody has any suggestions, please? :) @chrisdonahue @andimarafioti