Initial upload of RVC voice model
Browse files- .gitattributes +1 -0
- Bubble-Buddy_200e_4400s.pth +3 -0
- README.md +32 -3
- config.json +75 -0
- model_info.json +6 -0
- my-project.index +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
my-project.index filter=lfs diff=lfs merge=lfs -text
|
Bubble-Buddy_200e_4400s.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8d4fb8b1593d72adf9747a44871aa490d4a56fd4c1513cd47dcc1fcde74b01
|
| 3 |
+
size 55224639
|
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
-
-
|
| 2 |
-
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BubbleBuddy-Style RVC Voice Model
|
| 2 |
+
|
| 3 |
+
This repository contains an **RVC (Retrieval-based Voice Conversion) voice model**
|
| 4 |
+
trained to reproduce a **cartoon-style voice inspired by Bubble Buddy**.
|
| 5 |
+
|
| 6 |
+
## Disclaimer
|
| 7 |
+
This model is:
|
| 8 |
+
- NOT official
|
| 9 |
+
- NOT affiliated with Nickelodeon or SpongeBob SquarePants
|
| 10 |
+
- NOT endorsed by any rights holder
|
| 11 |
+
|
| 12 |
+
This model is provided for **research, parody, and educational use only**.
|
| 13 |
+
|
| 14 |
+
Do not use this model to:
|
| 15 |
+
- Impersonate real people
|
| 16 |
+
- Claim official character dialogue
|
| 17 |
+
- Violate copyright laws or platform rules
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
- Model type: RVC
|
| 21 |
+
- Epochs: 200
|
| 22 |
+
- Sample rate: 44kHz
|
| 23 |
+
- Files included:
|
| 24 |
+
- `.pth` model
|
| 25 |
+
- `.index` feature index
|
| 26 |
+
- `config.json`
|
| 27 |
+
|
| 28 |
+
## Usage
|
| 29 |
+
Load the model using an RVC-compatible inference UI or script.
|
| 30 |
+
|
| 31 |
+
## License
|
| 32 |
+
CC BY-NC 4.0 (Non-commercial use only)
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"log_interval": 200,
|
| 4 |
+
"seed": 1234,
|
| 5 |
+
"learning_rate": 0.0001,
|
| 6 |
+
"betas": [
|
| 7 |
+
0.8,
|
| 8 |
+
0.99
|
| 9 |
+
],
|
| 10 |
+
"eps": 1e-09,
|
| 11 |
+
"lr_decay": 0.999875,
|
| 12 |
+
"segment_size": 12800,
|
| 13 |
+
"c_mel": 45,
|
| 14 |
+
"c_kl": 1.0
|
| 15 |
+
},
|
| 16 |
+
"data": {
|
| 17 |
+
"max_wav_value": 32768.0,
|
| 18 |
+
"sample_rate": 40000,
|
| 19 |
+
"filter_length": 2048,
|
| 20 |
+
"hop_length": 400,
|
| 21 |
+
"win_length": 2048,
|
| 22 |
+
"n_mel_channels": 125,
|
| 23 |
+
"mel_fmin": 0.0,
|
| 24 |
+
"mel_fmax": null
|
| 25 |
+
},
|
| 26 |
+
"model": {
|
| 27 |
+
"inter_channels": 192,
|
| 28 |
+
"hidden_channels": 192,
|
| 29 |
+
"filter_channels": 768,
|
| 30 |
+
"text_enc_hidden_dim": 768,
|
| 31 |
+
"n_heads": 2,
|
| 32 |
+
"n_layers": 6,
|
| 33 |
+
"kernel_size": 3,
|
| 34 |
+
"p_dropout": 0,
|
| 35 |
+
"resblock": "1",
|
| 36 |
+
"resblock_kernel_sizes": [
|
| 37 |
+
3,
|
| 38 |
+
7,
|
| 39 |
+
11
|
| 40 |
+
],
|
| 41 |
+
"resblock_dilation_sizes": [
|
| 42 |
+
[
|
| 43 |
+
1,
|
| 44 |
+
3,
|
| 45 |
+
5
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
1,
|
| 49 |
+
3,
|
| 50 |
+
5
|
| 51 |
+
],
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
3,
|
| 55 |
+
5
|
| 56 |
+
]
|
| 57 |
+
],
|
| 58 |
+
"upsample_rates": [
|
| 59 |
+
10,
|
| 60 |
+
10,
|
| 61 |
+
2,
|
| 62 |
+
2
|
| 63 |
+
],
|
| 64 |
+
"upsample_initial_channel": 512,
|
| 65 |
+
"upsample_kernel_sizes": [
|
| 66 |
+
16,
|
| 67 |
+
16,
|
| 68 |
+
4,
|
| 69 |
+
4
|
| 70 |
+
],
|
| 71 |
+
"use_spectral_norm": false,
|
| 72 |
+
"gin_channels": 256,
|
| 73 |
+
"spk_embed_dim": 109
|
| 74 |
+
}
|
| 75 |
+
}
|
model_info.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_dataset_duration": "00:03:09",
|
| 3 |
+
"total_seconds": 189.73,
|
| 4 |
+
"embedder_model": "contentvec",
|
| 5 |
+
"speakers_id": 1
|
| 6 |
+
}
|
my-project.index
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dfe68cd608fe8c02eca5db337c862710af3d6d05a7383695a061f816f1aa9ac
|
| 3 |
+
size 32383259
|