whitneyten
/

whitneyTest

speaker-diarization

speaker-segmentation

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

whitneyten commited on Mar 20, 2025

Commit

7386757

·

verified ·

1 Parent(s): 351a2bb

End of training

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -25,12 +25,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the speaker-segmentation dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3704
-- Model Preparation Time: 0.0044
-- Der: 0.1155
-- False Alarm: 0.0620
-- Missed Detection: 0.0226
-- Confusion: 0.0309
 ## Model description
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
-| 0.6461        | 1.0   | 47   | 0.4057          | 0.0044                 | 0.1306 | 0.0644      | 0.0200           | 0.0463    |
-| 0.5281        | 2.0   | 94   | 0.3752          | 0.0044                 | 0.1212 | 0.0624      | 0.0230           | 0.0358    |
-| 0.4805        | 3.0   | 141  | 0.3693          | 0.0044                 | 0.1140 | 0.0626      | 0.0202           | 0.0312    |
-| 0.4664        | 4.0   | 188  | 0.3706          | 0.0044                 | 0.1149 | 0.0616      | 0.0229           | 0.0304    |
-| 0.4654        | 5.0   | 235  | 0.3704          | 0.0044                 | 0.1155 | 0.0620      | 0.0226           | 0.0309    |
 ### Framework versions

 This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the speaker-segmentation dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3691
+- Model Preparation Time: 0.0185
+- Der: 0.1163
+- False Alarm: 0.0627
+- Missed Detection: 0.0220
+- Confusion: 0.0315
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
+| 0.6461        | 1.0   | 47   | 0.4010          | 0.0185                 | 0.1278 | 0.0638      | 0.0228           | 0.0412    |
+| 0.5209        | 2.0   | 94   | 0.3736          | 0.0185                 | 0.1200 | 0.0612      | 0.0236           | 0.0351    |
+| 0.4799        | 3.0   | 141  | 0.3710          | 0.0185                 | 0.1165 | 0.0636      | 0.0207           | 0.0322    |
+| 0.4621        | 4.0   | 188  | 0.3699          | 0.0185                 | 0.1163 | 0.0621      | 0.0226           | 0.0315    |
+| 0.4649        | 5.0   | 235  | 0.3691          | 0.0185                 | 0.1163 | 0.0627      | 0.0220           | 0.0315    |
 ### Framework versions