Description
### this is a re-upload cause *SOMEONE "accidentally"* deleted the <#1175430844685484042> channel < Epochs: 1000 Steps: i fogor :3 RVC v2 Batch Size 14 Dataset size: 3 minutes all infers are transpose 0 files were 11kHz so i had to upscale using RX *Spectral Recovery*
Comments
I wonder if this includes the scientist screams
it did
idk if the pitch extraction included it but ya they were in the dataset
I wonder if you could get a sample using the model to make him scream?
lemme try
what input do i do
I included the screaming with my mommy long legs model yet she can't scream
maybe it was too little or Pitch extraction step didnt include it
yeah it was only a few audios of her screaming
then ye prob got ignored or smth
ok but what do i use to infer smth
cause the scientists had a distinct scream
the input audio for converting the voice
lemme look for somthin
okie dokie
I just had the biggist brain idea try and find a clip of plankton screaming
oh noes
ok lemme try
as expected
it cant do long screams ig maybe short screams or just shouting
sadly
yea
;3
what ;3
thats racist man 😔
nuh uh
Add a comment
Duplicate Model Detected
Not searchable or counted towards user score
Earlier copies of this model
Samples
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
More to explore
Loading more