sbkim052

How many people does multi-speaker tts can afford on the demo version?

Any plan to share the pre-trained models?

24

Hi, thanks for sharing this wonderful code. Do you have any plans to share the pre-trained models?

Making zero-shot model

1

Thank you for sharing your work. When i am to make zero shot model, should i train speaker embedder as well as the conversion model with large dataset (VCTK)? Or...

"The provided training data is very small for code verification purpose only"

9

Is this mean the pre-trained model given is kind of overfitted model trained on small dataset?

Does this work with the unseen speech?

3

Thank you for sharing your git. My question is same above. Does this work with the unseen speech?

where can i find args.yaml file?

1

where can i find args.yaml file? I have no idea. Can anybody help me?

Has anyone successfully trained on COCO?

5

Hello, thank you for sharing this code. I used the code with no changes and when I saw the visualization of the generated boxes are not really good.  ...

Hi, thank you for the great work. I have two questions. #### python train.py -train_dir your-path-to-npy-dir -m vqvc+ -n 64 -ch 512 -t train_simple_normalize #### with the above command, can...

Sorry to ask about a really simple question. Why is the number of the coco-stuff class 184? Isn't it 183 including the "unlabeled"?

Thank you for sharing this code. I have a question about the meaning of "multi-modality". Does "multi-modality" mean that the model acts as a classifier regardless of the input type?...