Zak and Wheezie (Dragon Tales), Trained

Create

Zak and Wheezie (Dragon Tales), Trained

FictionalRVC v2English
xhepyxopila user image
xhepyxopila
1 year ago
👀

519

👍

6

🪄

90

Description

Rediscovered this show thanks to theodd1sout I vaugley remember watching this show as a kid a few times and from what little I remember these 2 were my favorite. Was originally just gonna do one of them but then I quickly realized "oh shit i'm gonna have to do both" Datasets are both 1 minute (give or take) taken from a clip compilation I found focused on them specifically it luckily had a bit of singing data I could use in it. Though I didn't remember what they sounded like I found out with a combination of my memory and context. Zak: Wheezie:

Comments

xhepyxopila user image
xhepyxopila
1 year ago

Rediscovered this show thanks to theodd1sout, I vaugley remember watching this show as a kid a few times and from what little I remember these 2 were my favorite. Was originally just gonna do one of them but then I quickly realized "oh shit i'm gonna have to do both" Datasets are both 1 minute (give or take) taken from a clip compilation I found focused on them specifically, it luckily had a bit of singing data I could use in it. Though I didn't remember what they sounded like, I found out with a combination of my memory and context. Zak: https://huggingface.co/Xhepyxopila/MiscCartoonModelsRVC/resolve/main/Zak.zip Wheezie: https://huggingface.co/Xhepyxopila/MiscCartoonModelsRVC/resolve/main/Wheezie.zip

xhepyxopila user image
xhepyxopila
1 year ago

don't usually share examples like this, but I liked this one enough to share it here. Made FnF chromatics using these models + some audio SaltyDKDan recorded for people to make a scale out of him.

xhepyxopila user image
xhepyxopila
1 year ago

i REALLY love how this one turned out

thataiguy user image
thataiguy
1 year ago

Wheezie: (+6 for both instrumental and vocals)

thataiguy user image
thataiguy
1 year ago

Interesting results...

thataiguy user image
thataiguy
1 year ago

I'm not sure if its due to the dataset, or rvc v2 48k, or whatever could be causing it, but the Zhepy models sound better than the Clementine ones.

thataiguy user image
thataiguy
1 year ago

Like theres more detail in the voice.

xhepyxopila user image
xhepyxopila
1 year ago

the weird thing about this to me is that they used 48k RMVPE with a 9x longer dataset and somehow my models sound better

thataiguy user image
thataiguy
1 year ago

It could be two things.

thataiguy user image
thataiguy
1 year ago

1. singing data might not be in the other model.

thataiguy user image
thataiguy
1 year ago

2. RVMPE isn't as good with detail compared to mangocrepe.

thataiguy user image
thataiguy
1 year ago

3. 48k could cause issues with some datasets causing artifacts.

thataiguy user image
thataiguy
1 year ago

4. whatever the source and clean up that was used.

thataiguy user image
thataiguy
1 year ago

Checking a talking test, its the same results here.

thataiguy user image
thataiguy
1 year ago

_1 tests are yours.

thataiguy user image
thataiguy
1 year ago

and the standard name ones are Clementines.

xhepyxopila user image
xhepyxopila
1 year ago

honestly i couldn't tell much of a diffrence at first

xhepyxopila user image
xhepyxopila
1 year ago

but then i listened closer

thataiguy user image
thataiguy
1 year ago

Would be curious to see if you make an Ord and Cassie model uf they have similar differences.

xhepyxopila user image
xhepyxopila
1 year ago

maybe at some point i will

Add a comment

Samples

New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English

Pitch

Selected Audio
Selected Audio