Upload 2 files (#11)

- Upload 2 files (3fc5d26aaf8d44dc66990a8860e450756b3ae0af)


Co-authored-by: Trinh <vtrinh@users.noreply.huggingface.co>

.gitattributes

@@ -37,3 +37,4 @@ VoiceChat-v1-TC[[:space:]]voicechatv1.png filter=lfs diff=lfs merge=lfs -text
 interruptions.wav filter=lfs diff=lfs merge=lfs -text
 tool_call.wav filter=lfs diff=lfs merge=lfs -text
 turn_taking.wav filter=lfs diff=lfs merge=lfs -text
+demo.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -15,6 +15,10 @@ base_model:
 | Barge-in / interruption | User cuts in; model yields instantly | <audio controls src="https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/resolve/main/interruptions.wav"></audio> |
 | Tool calling live | Tools are called when needed | <audio controls src="https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/resolve/main/tool_call.wav"></audio> |
 
+▶ **Watch it in action.**
+
+<video controls src="https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/resolve/main/demo.mp4"></video>
+
 ▶ **Code:** On [Github](https://github.com/NVIDIA-NeMo/Speech/tree/nemotron-labs-voicechat)
 
 

demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab9ee7613d2c5fd30da07a700a0e5d72944c1ca12059e830dd95475143ad42a
+size 6801278