metadata
license: mit
base_model: pyannote/segmentation-3.0
tags:
- speaker-diarization
- speaker-segmentation
- generated_from_trainer
datasets:
- diarizers-community/callhome
model-index:
- name: speaker-segmentation-fine-tuned-callhome-eng
results: []
speaker-segmentation-fine-tuned-callhome-eng
This model is a fine-tuned version of pyannote/segmentation-3.0 on the diarizers-community/callhome eng dataset. It achieves the following results on the evaluation set:
- Loss: 0.4592
- Der: 0.1801
- False Alarm: 0.0585
- Missed Detection: 0.0704
- Confusion: 0.0512
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
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|
| 0.4101 | 1.0 | 362 | 0.4686 | 0.1875 | 0.0544 | 0.0788 | 0.0543 |
| 0.3867 | 2.0 | 724 | 0.4671 | 0.1858 | 0.0605 | 0.0708 | 0.0544 |
| 0.3777 | 3.0 | 1086 | 0.4603 | 0.1817 | 0.0554 | 0.0737 | 0.0526 |
| 0.3557 | 4.0 | 1448 | 0.4635 | 0.1815 | 0.0594 | 0.0700 | 0.0521 |
| 0.3517 | 5.0 | 1810 | 0.4592 | 0.1801 | 0.0585 | 0.0704 | 0.0512 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1