Hugging Face's logo

FluidInference
/
silero-vad-coreml

Voice Activity Detection
Core ML
English
audio
silero
speech
ios
macos
swift
Model card Files
xet
Community
1
bweng commited on
Commit
26ad3db
·
verified ·
1 Parent(s): f0afdda

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -50,13 +50,15 @@ FluidAudio
50
 
51
  This is how the model performs against the silero-vad v6.0.0 basline Pytorch JIT version
52
 
53
- ![comparison.png](comparison.png)
 
 
54
 
55
  Note that we tested the quantized versions, as the model is already tiny, theres no performance imporvement at all.
56
 
57
 
58
  This is how the different models compare in terms of speed, the 256s takes in 8 chunks of 32ms and processes it in batches so its much faster
59
- ![speed.png](speed.png)
60
 
61
 
62
 
 
50
 
51
  This is how the model performs against the silero-vad v6.0.0 basline Pytorch JIT version
52
 
53
+
54
+ ![graphs/yc_standard_comparison_20250915_205721_2c04b81.png](graphs/yc_standard_comparison_20250915_205721_2c04b81.png)
55
+ ![graphs/yc_256ms_comparison_20250915_205721_2c04b81.png](graphs/yc_256ms_comparison_20250915_205721_2c04b81.png)
56
 
57
  Note that we tested the quantized versions, as the model is already tiny, theres no performance imporvement at all.
58
 
59
 
60
  This is how the different models compare in terms of speed, the 256s takes in 8 chunks of 32ms and processes it in batches so its much faster
61
+ ![graphs/yc_performance_20250915_205721_2c04b81.png](graphs/yc_performance_20250915_205721_2c04b81.png)
62
 
63
 
64