Release models or provide small librispeech recipe?

Question

Release models or provide small librispeech recipe?

turian opened this issue 4 years ago · 4 comments

Since the VCC data is not commonly available could you either:

Release your pretrained models or
Add a VCTK / LibriSpeech recipe? (Since that data is available freely)

Answer 1 · 2021-05-15T17:29:23.000Z

We can consider adding VCTK recipes. Meanwhile, both VCC2018 and VCC2020 are publicly available, and we support the automatic downloading of the dataset in the VCC2018 recipe (not yet for VCC2020).

Answer 2 · 2021-05-15T17:46:10.000Z

@unilight Ah, the README says: "Note that dataset is only released for the participants (2020/05/26)." Do you want me to submit a PR to fix it, or would you?

Answer 3 · 2021-05-15T17:47:18.000Z

Would also be nice if the README explained what you said: "both VCC2018 and VCC2020 are publicly available, and we support the automatic downloading of the dataset in the VCC2018 recipe (not yet for VCC2020)."

Answer 4 · 2021-05-18T13:52:10.000Z

@unilight Do you have pretrained models you can share?