Frederico S. Oliveira

icon indicating a website link https://www.fredso.com.br icon indicating an email [email protected]

icon company UFMT icon location Cuiabá, Mato Grosso - Brazil icon location Researcher in the area of NLP, Ph.D. student at UFG, focusing on speech synthesis and recognition using deep learning and also professor at UFMT.

Results 9 comments of Frederico S. Oliveira

How do I upsample a wav once the model is trained?

Yes, checkpoints available at https://github.com/mindslab-ai/nuwave/issues/18.

Contribution: checkpoints AVAILABLE!

I also ran the test scripts: **nuwave_x2:** ![Captura de tela_2022-04-12_10-49-08](https://user-images.githubusercontent.com/6883434/162977286-2c9558b1-db5f-4f4f-8108-a34fa34a77a0.png) **nuwave_x3:** ![Captura de tela_2022-04-12_10-48-49](https://user-images.githubusercontent.com/6883434/162977324-19952108-2952-4438-b7b9-d6e157619917.png)

About to be a Contribution

Sorry, I trained the model but I ran out of time and didn't even get to test the checkpoints. Can you share jupyter notebook? For x2 the model worked?

About to be a Contribution

@dutchsing009 [email protected]

Guide on running the code.

Has anyone been able to execute this code? Please, I need help!

HuggingFace Version

@leng-yue how did you convert to huggingface? I trained my own version of contentvec and using the "**transformers/src/transformers/models/hubert/convert_hubert_original_pytorch_checkpoint_to_pytorch.py**" script to convert it, however I am getting this error message: >...

HuggingFace Version

@leng-yue Great! Thanks!

How to get a new spk2info.dict?

I developed this script that uses parselmouth or pyreaper. It needs some adjustments, because I'm creating the embeddings for all the files, and in the original I believe that an...

finetuning code?

+1