|
--- |
|
language: |
|
- en |
|
- ja |
|
tags: |
|
- rvc |
|
- voice cloning |
|
- The Amazing World of Gumball |
|
- おかしなガムボール |
|
- Gumball Watterson |
|
- ガムボール |
|
- Junko Takeuchi |
|
- 竹内順子 |
|
--- |
|
|
|
## Model Details |
|
|
|
Voice of Junko Takeuchi 竹内順子 as Gumball Watterson ガムボール in the Japanese dub of the cartoon The Amazing World of Gumball おかしなガムボール. |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
- **Developed by:** [ijik-loker](https://huggingface.co/ijik-loker) |
|
- **Model type:** [Retrieval-based Voice Conversion (RVC)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) |
|
- **Language(s):** Japanese |
|
|
|
## Uses |
|
|
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> |
|
|
|
Used in the popular Retrieval-based Voice Conversion WebUI via inference or real-time using [Voice Changer](https://github.com/w-okada/voice-changer). |
|
The index file should be used alongside the model. |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
|
|
#### Voice clips dataset total duration |
|
|
|
v1 model: 07min 35s |
|
|
|
v2 model: 17min 22s |
|
|
|
Trained using [episode clips](https://www.youtube.com/playlist?list=PLWSC6OHatntSWjsbQWCSQn-MuwIscHL_8) uploaded by CartoonNetworkJP カートゥーン ネットワーク: |
|
1. [The Watch](https://youtu.be/qn8M_KHPYno?si=6y02GSGaaY6zYTIa) |
|
2. [The Void](https://youtu.be/Cxtg7LqmdkI?si=mGws0GXpV3K8yt6C) |
|
3. [The Vegging](https://youtu.be/egUkeiy5Ujw?si=KoVwqrbduXTUdMfH) |
|
4. [The Test](https://youtu.be/e3t0yldGmTw?si=DduDKGu1D1H39YCV) |
|
5. [The Tape](https://youtu.be/3g6if7EhZNY?si=68lTnBIdYNH4n6fN) |
|
6. [The Stories](https://youtu.be/c4yw042zJXA?si=yXs5vjyhHvgRkAjv) |
|
7. [The Slide](https://youtu.be/KF-gZK8859Q?si=ls8KaPAhlYB4tGGo) |
|
8. [The Sidekick](https://youtu.be/3vfZauRDqG4?si=yDHBpTF-7pm0x3gt) |
|
9. [The Safety](https://youtu.be/hZT9I0TVpJk?si=eF2Xs8PT0xTSw1Oe) |
|
10. [The Puppets](https://youtu.be/TH_JMIkCWTc?si=QaW3rmEJgWC_Msdq) |
|
11. [The Procrastinators](https://youtu.be/FGH3-NR22YI?si=t7Ux_7ccgmqbixE7) |
|
12. [The Pest](https://youtu.be/V1De2RI2q_E?si=i-GbCoy_eUxtdJbL) |
|
13. [The Nobody](https://youtu.be/qC7Z1QigFLA?si=sO_WwgOGcf-krHI0) |
|
14. [The Misunderstandings](https://youtu.be/7GOmjuB0aLk?si=5cb0XSKL3V3GwFEQ) |
|
15. [The Matchmaker](https://youtu.be/_x-Czj3G8rc?si=rwAJC58492pDUR9P) |
|
16. [The Burden](https://youtu.be/GN5c9FUbZMk?si=zZYkWAR8Z4GT0Ev_) |
|
17. [The Best](https://youtu.be/LN2AyPry0hI?si=tdgIUw22f2o2kTv9) |
|
|
|
### Training Procedure |
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
1. Remove noise using [Ultimate Vocal Remover 5](https://github.com/Anjok07/ultimatevocalremovergui) UVR-DeNoise. |
|
2. Extract vocals using RVC Web UI [HP5-主旋律人声vocals+其他instrumentals.pth](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/uvr5_weights/HP5-%E4%B8%BB%E6%97%8B%E5%BE%8B%E4%BA%BA%E5%A3%B0vocals%2B%E5%85%B6%E4%BB%96instrumentals.pth). |
|
3. Remove echo and reverb using Ultimate Vocal Remover 5 UVR-DeEcho-DeReverb. |
|
4. Manually diarise voices in [Audacity](https://www.audacityteam.org/) using labels. |
|
5. Export multiple to .wav by labels. |
|
6. Train using RVC |
|
* Target Sample Rate: 48k |
|
* Version: v2 |
|
* Total training epochs: 200 |
|
* Base model G: f0G48k.pth |
|
* Base model D: f0D48k.pth |
|
|
