update image paths
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ license: apache-2.0
|
|
| 4 |
# Zonos-v0.1
|
| 5 |
|
| 6 |
<div align="center">
|
| 7 |
-
<img src="https://github.com/Zyphra/Zonos/blob/main/
|
| 8 |
alt="Title card"
|
| 9 |
style="width: 500px;
|
| 10 |
height: auto;
|
|
@@ -18,7 +18,7 @@ It enables highly naturalistic speech generation from text prompts when given a
|
|
| 18 |
Trained on approximately 200,000 hours of primarily English speech data, Zonos follows a straightforward architecture: text normalization and phonemization via eSpeak, followed by DAC token prediction through a transformer or hybrid backbone. An architecture overview can be seen below.
|
| 19 |
|
| 20 |
<div align="center">
|
| 21 |
-
<img src="https://github.com/Zyphra/Zonos/blob/main/
|
| 22 |
alt="Architecture diagram"
|
| 23 |
style="width: 1000px;
|
| 24 |
height: auto;
|
|
|
|
| 4 |
# Zonos-v0.1
|
| 5 |
|
| 6 |
<div align="center">
|
| 7 |
+
<img src="https://github.com/Zyphra/Zonos/blob/main/assets/ZonosHeader.png?raw=true"
|
| 8 |
alt="Title card"
|
| 9 |
style="width: 500px;
|
| 10 |
height: auto;
|
|
|
|
| 18 |
Trained on approximately 200,000 hours of primarily English speech data, Zonos follows a straightforward architecture: text normalization and phonemization via eSpeak, followed by DAC token prediction through a transformer or hybrid backbone. An architecture overview can be seen below.
|
| 19 |
|
| 20 |
<div align="center">
|
| 21 |
+
<img src="https://github.com/Zyphra/Zonos/blob/main/assets/ArchitectureDiagram.png?raw=true"
|
| 22 |
alt="Architecture diagram"
|
| 23 |
style="width: 1000px;
|
| 24 |
height: auto;
|