Update README.md
Browse files
README.md
CHANGED
@@ -1,42 +1,164 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
-
- en
|
5 |
tags:
|
6 |
-
- ai
|
7 |
-
- rvc
|
8 |
-
- vc
|
9 |
-
- voice-cloning
|
10 |
-
- applio
|
11 |
-
- titan
|
12 |
-
- pretrained
|
13 |
datasets:
|
14 |
-
- blaise-tk/TITAN-Medium
|
15 |
pipeline_tag: audio-to-audio
|
16 |
---
|
|
|
17 |
# TITAN: A Versatile, Robust, and High-Quality Pretrained Model for Retrieval-based Voice Conversion (RVC) Training
|
18 |
|
19 |
## Overview
|
|
|
20 |
TITAN is a state-of-the-art pretrained model designed for Retrieval-based Voice Conversion (https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/) training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing high-quality results with minimal training effort.
|
21 |
|
22 |
## Model Details
|
|
|
23 |
### Titan-Medium
|
|
|
24 |
- Training Environment: Utilized a RTX 3060 TI on Applio v3.1.1 (https://github.com/IAHispano/Applio), employing a batch size of 8 over a span of 3 weeks.
|
25 |
- Iterations: X Steps
|
26 |
- Epochs: X
|
27 |
- Sampling rate: 40k, 32k (still training)
|
28 |
- Fine-tuning Process: RVC v2 pretrained with pitch guidance, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725) also available on [datasets/blaise-tk/TITAN-Medium](https://huggingface.co/datasets/blaise-tk/TITAN-Medium).
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
### Titan-Large
|
|
|
31 |
- Details forthcoming...
|
32 |
|
33 |
## Collaborators
|
|
|
34 |
We appreciate the contributions of our collaborators who have helped in the development and refinement of TITAN.
|
35 |
|
36 |
- Mustar
|
37 |
- SimplCup
|
38 |
|
39 |
## Beta Testers
|
|
|
40 |
We extend our gratitude to the beta testers who provided valuable feedback during the testing phase of TITAN.
|
41 |
|
42 |
- SimplCup
|
@@ -45,6 +167,7 @@ We extend our gratitude to the beta testers who provided valuable feedback durin
|
|
45 |
- SCRFilms
|
46 |
|
47 |
## Citation
|
|
|
48 |
Should you find TITAN beneficial for your research endeavors or projects, we kindly request citing our repository:
|
49 |
|
50 |
```
|
@@ -56,4 +179,4 @@ Should you find TITAN beneficial for your research endeavors or projects, we kin
|
|
56 |
publisher={Blaise},
|
57 |
url={https://huggingface.co/blaise-tk/TITAN/}
|
58 |
}
|
59 |
-
```
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
+
- en
|
5 |
tags:
|
6 |
+
- ai
|
7 |
+
- rvc
|
8 |
+
- vc
|
9 |
+
- voice-cloning
|
10 |
+
- applio
|
11 |
+
- titan
|
12 |
+
- pretrained
|
13 |
datasets:
|
14 |
+
- blaise-tk/TITAN-Medium
|
15 |
pipeline_tag: audio-to-audio
|
16 |
---
|
17 |
+
|
18 |
# TITAN: A Versatile, Robust, and High-Quality Pretrained Model for Retrieval-based Voice Conversion (RVC) Training
|
19 |
|
20 |
## Overview
|
21 |
+
|
22 |
TITAN is a state-of-the-art pretrained model designed for Retrieval-based Voice Conversion (https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/) training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing high-quality results with minimal training effort.
|
23 |
|
24 |
## Model Details
|
25 |
+
|
26 |
### Titan-Medium
|
27 |
+
|
28 |
- Training Environment: Utilized a RTX 3060 TI on Applio v3.1.1 (https://github.com/IAHispano/Applio), employing a batch size of 8 over a span of 3 weeks.
|
29 |
- Iterations: X Steps
|
30 |
- Epochs: X
|
31 |
- Sampling rate: 40k, 32k (still training)
|
32 |
- Fine-tuning Process: RVC v2 pretrained with pitch guidance, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725) also available on [datasets/blaise-tk/TITAN-Medium](https://huggingface.co/datasets/blaise-tk/TITAN-Medium).
|
33 |
|
34 |
+
#### Samples
|
35 |
+
|
36 |
+
<table style="width:100%; text-align:center;">
|
37 |
+
<tr>
|
38 |
+
<th>Titan-Medium</th>
|
39 |
+
<th>Ov2</th>
|
40 |
+
<th>Ov2.1</th>
|
41 |
+
</tr>
|
42 |
+
<tr>
|
43 |
+
<td>
|
44 |
+
<audio controls>
|
45 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 1 - Titan.wav?download=true" type="audio/wav">
|
46 |
+
Your browser does not support the audio element.
|
47 |
+
</audio>
|
48 |
+
</td>
|
49 |
+
<td>
|
50 |
+
<audio controls>
|
51 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 1 - Ov2.wav?download=true" type="audio/wav">
|
52 |
+
Your browser does not support the audio element.
|
53 |
+
</audio>
|
54 |
+
</td>
|
55 |
+
</tr>
|
56 |
+
|
57 |
+
</tr>
|
58 |
+
<tr>
|
59 |
+
<td>
|
60 |
+
<audio controls>
|
61 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 2 - Titan.wav?download=true" type="audio/wav">
|
62 |
+
Your browser does not support the audio element.
|
63 |
+
</audio>
|
64 |
+
</td>
|
65 |
+
<td>
|
66 |
+
<audio controls>
|
67 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 2 - Ov2.wav?download=true" type="audio/wav">
|
68 |
+
Your browser does not support the audio element.
|
69 |
+
</audio>
|
70 |
+
</td>
|
71 |
+
</tr>
|
72 |
+
|
73 |
+
<tr>
|
74 |
+
<td>
|
75 |
+
<audio controls>
|
76 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 2 - Test 1 - Titan.wav?download=true" type="audio/wav">
|
77 |
+
Your browser does not support the audio element.
|
78 |
+
</audio>
|
79 |
+
</td>
|
80 |
+
<td>
|
81 |
+
<audio controls>
|
82 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 2 - Test 1 - Ov2.wav?download=true" type="audio/wav">
|
83 |
+
Your browser does not support the audio element.
|
84 |
+
</audio>
|
85 |
+
</td>
|
86 |
+
|
87 |
+
</tr>
|
88 |
+
<tr>
|
89 |
+
<td>
|
90 |
+
<audio controls>
|
91 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 2 - Test 2 - Titan.wav?download=true" type="audio/wav">
|
92 |
+
Your browser does not support the audio element.
|
93 |
+
</audio>
|
94 |
+
</td>
|
95 |
+
<td>
|
96 |
+
<audio controls>
|
97 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 2 - Test 2 - Ov2.wav?download=true" type="audio/wav">
|
98 |
+
Your browser does not support the audio element.
|
99 |
+
</audio>
|
100 |
+
</td>
|
101 |
+
</tr>
|
102 |
+
|
103 |
+
</tr>
|
104 |
+
<tr>
|
105 |
+
<td>
|
106 |
+
<audio controls>
|
107 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 1 - Titan.wav?download=true" type="audio/wav">
|
108 |
+
Your browser does not support the audio element.
|
109 |
+
</audio>
|
110 |
+
</td>
|
111 |
+
<td>
|
112 |
+
<audio controls>
|
113 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 1 - Ov2.wav?download=true" type="audio/wav">
|
114 |
+
Your browser does not support the audio element.
|
115 |
+
</audio>
|
116 |
+
</td>
|
117 |
+
<td>
|
118 |
+
<audio controls>
|
119 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 1 - Ov2.1.wav?download=true" type="audio/wav">
|
120 |
+
Your browser does not support the audio element.
|
121 |
+
</audio>
|
122 |
+
</td>
|
123 |
+
</tr>
|
124 |
+
|
125 |
+
</tr>
|
126 |
+
<tr>
|
127 |
+
<td>
|
128 |
+
<audio controls>
|
129 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 2 - Titan.wav?download=true" type="audio/wav">
|
130 |
+
Your browser does not support the audio element.
|
131 |
+
</audio>
|
132 |
+
</td>
|
133 |
+
<td>
|
134 |
+
<audio controls>
|
135 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 2 - Ov2.wav?download=true" type="audio/wav">
|
136 |
+
Your browser does not support the audio element.
|
137 |
+
</audio>
|
138 |
+
</td>
|
139 |
+
<td>
|
140 |
+
<audio controls>
|
141 |
+
<source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 3 - Test 2 - Ov2.1.wav?download=true" type="audio/wav">
|
142 |
+
Your browser does not support the audio element.
|
143 |
+
</audio>
|
144 |
+
</td>
|
145 |
+
</tr>
|
146 |
+
|
147 |
+
</table>
|
148 |
+
|
149 |
### Titan-Large
|
150 |
+
|
151 |
- Details forthcoming...
|
152 |
|
153 |
## Collaborators
|
154 |
+
|
155 |
We appreciate the contributions of our collaborators who have helped in the development and refinement of TITAN.
|
156 |
|
157 |
- Mustar
|
158 |
- SimplCup
|
159 |
|
160 |
## Beta Testers
|
161 |
+
|
162 |
We extend our gratitude to the beta testers who provided valuable feedback during the testing phase of TITAN.
|
163 |
|
164 |
- SimplCup
|
|
|
167 |
- SCRFilms
|
168 |
|
169 |
## Citation
|
170 |
+
|
171 |
Should you find TITAN beneficial for your research endeavors or projects, we kindly request citing our repository:
|
172 |
|
173 |
```
|
|
|
179 |
publisher={Blaise},
|
180 |
url={https://huggingface.co/blaise-tk/TITAN/}
|
181 |
}
|
182 |
+
```
|