amirhosein-prdv/speaker-segmentation-fine-tuned-synthetic_v3
0372
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
speaker-segmentation-fine-tuned-synthetic_v3
This model is a fine-tuned version of pyannote/segmentation-3.0 on the uncleMehrzad/synthetic-speaker-diarization-dataset-fa-large-3000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5584
- Model Preparation Time: 0.0027
- Der: 0.1661
- False Alarm: 0.0517
- Missed Detection: 0.0375
- Confusion: 0.0769
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- trainbatchsize: 32
- evalbatchsize: 32
- seed: 42
- optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lrschedulertype: cosine
- num_epochs: 50.0
Training results
Framework versions
- Transformers 4.57.6
- Pytorch 2.14.0+cu126
- Datasets 5.0.1
- Tokenizers 0.22.2
