Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# FLM-Audio
|
| 2 |
FLM-Audio is a audio-language subversion of [RoboEgo/FLM-Ego](https://arxiv.org/abs/2506.01934v1) -- an omnimodal model with native full duplexity. It simultaneously listens, speaks, and composes internal monologue, delivering low‑latency, duplex conversational responses in both English and Chinese. FLM‑Audio is robust to noise and user interruptions, prioritizing responsiveness and naturalness.
|
| 3 |
|
|
@@ -87,7 +90,4 @@ If you find our work helpful, please consider citing the following papers.
|
|
| 87 |
journal={arXiv preprint arXiv:2506.01934},
|
| 88 |
year={2025}
|
| 89 |
}
|
| 90 |
-
```
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: audio-to-audio
|
| 3 |
+
---
|
| 4 |
# FLM-Audio
|
| 5 |
FLM-Audio is a audio-language subversion of [RoboEgo/FLM-Ego](https://arxiv.org/abs/2506.01934v1) -- an omnimodal model with native full duplexity. It simultaneously listens, speaks, and composes internal monologue, delivering low‑latency, duplex conversational responses in both English and Chinese. FLM‑Audio is robust to noise and user interruptions, prioritizing responsiveness and naturalness.
|
| 6 |
|
|
|
|
| 90 |
journal={arXiv preprint arXiv:2506.01934},
|
| 91 |
year={2025}
|
| 92 |
}
|
| 93 |
+
```
|
|
|
|
|
|
|
|
|