Hugging Face's logo

nvidia
/
Nemotron-3-Diarization

Voice Activity Detection
NeMo
Safetensors
GGUF
Transformers
nemotron3_diarization
audio-frame-classification
speaker-diarization
streaming-sortformer
speaker-tagging
Model card Files
xet
 Community
9
taejinp commited on
Commit
4f34df0
·
verified ·
1 Parent(s): e07ca82

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -6
README.md CHANGED
@@ -24,17 +24,15 @@ A single checkpoint supports input buffer latency as low as 80 ms for latency-cr
24
 
25
  September 23, 2026
26
 
 
 
 
 
27
  ## What does max 8-speaker diarization mean ?
28
 
29
  <video controls src="https://huggingface.co/nvidia/Nemotron-3-Diarization/resolve/main/nemotron3_tts_8_open_voices.mp4" width="100%"></video>
30
-
31
  ---
32
 
33
- ## Live Action Demo Page
34
-
35
- [HuggingFace Space: Nemotron-Diarization with Streaming ASR](https://huggingface.co/spaces/nvidia/nemotron-diarization)
36
-
37
-
38
  ## How to use this model
39
 
40
  ### NVIDIA NeMo Speech
 
24
 
25
  September 23, 2026
26
 
27
+ ## Live Action Demo Page
28
+
29
+ [![Nemotron-Diarization with Streaming ASR Demo](https://huggingface.co/nvidia/Nemotron-3-Diarization/resolve/main/streaming_diarization_demo.png)](https://huggingface.co/spaces/nvidia/nemotron-diarization)
30
+
31
  ## What does max 8-speaker diarization mean ?
32
 
33
  <video controls src="https://huggingface.co/nvidia/Nemotron-3-Diarization/resolve/main/nemotron3_tts_8_open_voices.mp4" width="100%"></video>
 
34
  ---
35
 
 
 
 
 
 
36
  ## How to use this model
37
 
38
  ### NVIDIA NeMo Speech