Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,16 @@ metrics:
|
|
| 21 |
</div>
|
| 22 |
|
| 23 |
<p align="center">
|
| 24 |
-
<font size="3"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
</p>
|
| 26 |
|
|
|
|
| 27 |
## Model Description
|
| 28 |
EchoX is a Speech-to-Speech large language model that addresses the acoustic-semantic gap. By introducing **Echo Training**, EchoX integrates semantic and acoustic learning, mitigating the degradation of reasoning ability observed in existing speech-based LLMs. It is trained on only 10k hours of data while delivering state-of-the-art results in knowledge-based question answering and speech interaction tasks.
|
| 29 |
|
|
|
|
| 21 |
</div>
|
| 22 |
|
| 23 |
<p align="center">
|
| 24 |
+
<font size="3">
|
| 25 |
+
<a href="https://github.com/FreedomIntelligence/EchoX">🐈⬛ Github</a> ｜ 
|
| 26 |
+
<a href="https://arxiv.org/abs/2509.09174">📃 Paper</a> ｜ 
|
| 27 |
+
<a href="https://huggingface.co/spaces/FreedomIntelligence/EchoX">🚀 Space</a> ｜ 
|
| 28 |
+
<a href="https://huggingface.co/datasets/FreedomIntelligence/EchoX-Dialougues">📊 EchoX-Dialougues</a> ｜ 
|
| 29 |
+
<a href="https://huggingface.co/datasets/KurtDu/EchoX-Dialogues-Plus">📊 EchoX-Dialogues-Plus</a>
|
| 30 |
+
</font>
|
| 31 |
</p>
|
| 32 |
|
| 33 |
+
|
| 34 |
## Model Description
|
| 35 |
EchoX is a Speech-to-Speech large language model that addresses the acoustic-semantic gap. By introducing **Echo Training**, EchoX integrates semantic and acoustic learning, mitigating the degradation of reasoning ability observed in existing speech-based LLMs. It is trained on only 10k hours of data while delivering state-of-the-art results in knowledge-based question answering and speech interaction tasks.
|
| 36 |
|