Hugging Face's logo

nvidia
/
diar_streaming_sortformer_4spk-v2.1

Automatic Speech Recognition
NeMo
PyTorch
speaker-diarization
speaker-recognition
speech
audio
Transformer
FastConformer
Conformer
NEST
NeMo
Eval Results
Model card Files
xet
taejinp commited on
Commit
3993374
·
1 Parent(s): ab2c546

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -7
README.md CHANGED
@@ -399,16 +399,13 @@ Data collection methods vary across individual datasets. For example, the above
399
 
400
  * All evaluations include overlapping speech.
401
  * Collar tolerance is 0s for DIHARD III Eval, and 0.25s for CALLHOME-part2 and CH109.
402
- * Post-Processing (PP) is optimized on two different held-out dataset splits.
403
- - [DIHARD III Dev Optimized Post-Processing](https://github.com/NVIDIA/NeMo/tree/main/examples/speaker_tasks/diarization/conf/post_processing/diar_streaming_sortformer_4spk-v2_dihard3-dev.yaml) for DIHARD III Eval
404
- - [CALLHOME-part1 Optimized Post-Processing](https://github.com/NVIDIA/NeMo/tree/main/examples/speaker_tasks/diarization/conf/post_processing/diar_streaming_sortformer_4spk-v2_callhome-part1.yaml) for CALLHOME-part2 and CH109
405
 
406
  # Dataset Evaluation Results
407
 
408
- | **Latency** | *PP* | **DIHARD III Eval <=4spk** | **DIHARD III Eval >=5spk** | **DIHARD III Eval full** | **CALLHOME-part2 2spk** | **CALLHOME-part2 3spk** | **CALLHOME-part2 4spk** | **CALLHOME-part2 5spk** | **CALLHOME-part2 6spk** | **CALLHOME-part2 full** | **CH109** | **AliMeeting Test near** | **AliMeeting Test far** | **AMI Test IHM** | **AMI Test SDM** | **NOTSOFAR1 Eval SC <=4spk** | **NOTSOFAR1 Eval SC >=5spk** |
409
- |-------------|------|----------------------------|----------------------------|--------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-----------|--------------------------|-------------------------|------------------|------------------|------------------------------|------------------------------|
410
- | 30.4s | no | 14.84 | 38.90 | 19.49 | 5.65 | 10.03 | 12.33 | 22.35 | 22.26 | 10.10 | 5.04 | 11.73 | 13.55 | 15.90 | 17.80 | 15.95 | 34.81 |
411
- | 1.04s | no | 15.09 | 41.42 | 20.21 | 6.65 | 11.25 | 13.35 | 22.12 | 24.51 | 11.19 | 5.09 | 12.60 | 15.60 | 16.67 | 20.57 | 17.26 | 36.76 |
412
 
413
 
414
 
 
399
 
400
  * All evaluations include overlapping speech.
401
  * Collar tolerance is 0s for DIHARD III Eval, and 0.25s for CALLHOME-part2 and CH109.
 
 
 
402
 
403
  # Dataset Evaluation Results
404
 
405
+ | **Latency** | **DIHARD III Eval <=4spk** | **DIHARD III Eval >=5spk** | **DIHARD III Eval full** | **CALLHOME-part2 2spk** | **CALLHOME-part2 3spk** | **CALLHOME-part2 4spk** | **CALLHOME-part2 5spk** | **CALLHOME-part2 6spk** | **CALLHOME-part2 full** | **CH109** | **AliMeeting Test near** | **AliMeeting Test far** | **AMI Test IHM** | **AMI Test SDM** | **NOTSOFAR1 Eval SC <=4spk** | **NOTSOFAR1 Eval SC >=5spk** |
406
+ |-------------|----------------------------|----------------------------|--------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-------------------------|-----------|--------------------------|-------------------------|------------------|------------------|------------------------------|------------------------------|
407
+ | 30.4s | 14.84 | 38.90 | 19.49 | 5.65 | 10.03 | 12.33 | 22.35 | 22.26 | 10.10 | 5.04 | 11.73 | 13.55 | 15.90 | 17.80 | 15.95 | 34.81 |
408
+ | 1.04s | 15.09 | 41.42 | 20.21 | 6.65 | 11.25 | 13.35 | 22.12 | 24.51 | 11.19 | 5.09 | 12.60 | 15.60 | 16.67 | 20.57 | 17.26 | 36.76 |
409
 
410
 
411