Update README.md
Browse files
README.md
CHANGED
|
@@ -136,6 +136,7 @@ base_model:
|
|
| 136 |
|
| 137 |
🚀 **FastSLM** is a designed for efficient speech-to-text transcription.
|
| 138 |
|
|
|
|
| 139 |
## 📌 Key Features (Safe Version)
|
| 140 |
|
| 141 |
* ⚡ Efficient long-form speech processing
|
|
@@ -143,10 +144,10 @@ base_model:
|
|
| 143 |
* ✅ Evaluation results on standard ASR benchmarks (WERs listed above)
|
| 144 |
* Low Speech Token Rate** 1.67 token/Sec.
|
| 145 |
* Bilingual support (Korean & English) in a single model
|
| 146 |
-
|
| 147 |
-
|
|
|
|
| 148 |
</p>
|
| 149 |
-
-->
|
| 150 |
|
| 151 |
## 🚀 Getting Started
|
| 152 |
|
|
|
|
| 136 |
|
| 137 |
🚀 **FastSLM** is a designed for efficient speech-to-text transcription.
|
| 138 |
|
| 139 |
+
|
| 140 |
## 📌 Key Features (Safe Version)
|
| 141 |
|
| 142 |
* ⚡ Efficient long-form speech processing
|
|
|
|
| 144 |
* ✅ Evaluation results on standard ASR benchmarks (WERs listed above)
|
| 145 |
* Low Speech Token Rate** 1.67 token/Sec.
|
| 146 |
* Bilingual support (Korean & English) in a single model
|
| 147 |
+
|
| 148 |
+
<p align="center">
|
| 149 |
+
<img src="HTA.png" width="1024" alt="HTA architecture">
|
| 150 |
</p>
|
|
|
|
| 151 |
|
| 152 |
## 🚀 Getting Started
|
| 153 |
|