Update README.md
Browse files
README.md
CHANGED
@@ -22,17 +22,49 @@ th, td {
|
|
22 |
font-weight: bold;
|
23 |
text-decoration: underline;
|
24 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
</style>
|
26 |
|
27 |
-
<div style="text-align: center; margin: 20px auto; padding:
|
28 |
-
<
|
29 |
-
|
30 |
-
|
31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
</div>
|
33 |
|
34 |
-
# OuteTTS-0.1-350M
|
35 |
-
|
36 |
## Model Description
|
37 |
|
38 |
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a straightforward approach using crafted prompts and audio tokens.
|
@@ -140,7 +172,8 @@ Listen to samples generated by OuteTTS-0.1-350M:
|
|
140 |
</div>
|
141 |
|
142 |
## Installation
|
143 |
-
|
|
|
144 |
|
145 |
```bash
|
146 |
pip install outetts
|
@@ -215,4 +248,4 @@ output = interface.generate(
|
|
215 |
By using this model, you acknowledge that you understand and assume the risks associated with its use.
|
216 |
You are solely responsible for ensuring compliance with all applicable laws and regulations.
|
217 |
We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages.
|
218 |
-
We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.
|
|
|
22 |
font-weight: bold;
|
23 |
text-decoration: underline;
|
24 |
}
|
25 |
+
.badges {
|
26 |
+
display: flex;
|
27 |
+
justify-content: center;
|
28 |
+
gap: 10px;
|
29 |
+
flex-wrap: wrap;
|
30 |
+
margin-top: 10px;
|
31 |
+
}
|
32 |
+
.badge {
|
33 |
+
text-decoration: none;
|
34 |
+
display: inline-block;
|
35 |
+
padding: 4px 8px;
|
36 |
+
border-radius: 5px;
|
37 |
+
color: #fff;
|
38 |
+
font-size: 12px;
|
39 |
+
font-weight: bold;
|
40 |
+
width: 250px;
|
41 |
+
}
|
42 |
+
.badge-hf-blue {
|
43 |
+
background-color: #767b81;
|
44 |
+
}
|
45 |
+
.badge-hf-pink {
|
46 |
+
background-color: #7b768a;
|
47 |
+
}
|
48 |
+
.badge-github {
|
49 |
+
background-color: #2c2b2b;
|
50 |
+
}
|
51 |
</style>
|
52 |
|
53 |
+
<div style="text-align: center; margin: 20px auto; padding: 10px; border: 2px solid #ddd; border-radius: 10px;">
|
54 |
+
<div style="margin-bottom: 20px;">
|
55 |
+
<h2 style="margin-bottom: 4px; margin-top: 0px;">OuteAI</h2>
|
56 |
+
<a href="https://www.outeai.com/" target="_blank" style="margin-right: 10px;">π OuteAI.com</a>
|
57 |
+
<a href="https://discord.gg/vyBM87kAmf" target="_blank" style="margin-right: 10px;">π€ Join our Discord</a>
|
58 |
+
<a href="https://x.com/OuteAI" target="_blank">π @OuteAI</a>
|
59 |
+
</div>
|
60 |
+
<div class="badges">
|
61 |
+
<a href="https://huggingface.co/OuteAI/OuteTTS-0.1-350M" target="_blank" class="badge badge-hf-blue">π€ Hugging Face - OuteTTS 0.1 350M</a>
|
62 |
+
<a href="https://huggingface.co/OuteAI/OuteTTS-0.1-350M-GGUF" target="_blank" class="badge badge-hf-blue">π€ Hugging Face - OuteTTS 0.1 350M GGUF</a>
|
63 |
+
<a href="https://huggingface.co/spaces/OuteAI/OuteTTS-0.1-350M-Demo" target="_blank" class="badge badge-hf-pink">π€ Hugging Face - Demo</a>
|
64 |
+
<a href="https://github.com/edwko/OuteTTS" target="_blank" class="badge badge-github">GitHub - OuteTTS</a>
|
65 |
+
</div>
|
66 |
</div>
|
67 |
|
|
|
|
|
68 |
## Model Description
|
69 |
|
70 |
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a straightforward approach using crafted prompts and audio tokens.
|
|
|
172 |
</div>
|
173 |
|
174 |
## Installation
|
175 |
+
|
176 |
+
[![GitHub](https://img.shields.io/badge/GitHub-OuteTTS-181717?logo=github)](https://github.com/edwko/OuteTTS)
|
177 |
|
178 |
```bash
|
179 |
pip install outetts
|
|
|
248 |
By using this model, you acknowledge that you understand and assume the risks associated with its use.
|
249 |
You are solely responsible for ensuring compliance with all applicable laws and regulations.
|
250 |
We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages.
|
251 |
+
We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.
|