metadata
language:
- eng
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 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4692
- Der: 0.1840
- False Alarm: 0.0616
- Missed Detection: 0.0711
- Confusion: 0.0513
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|
| 0.3907 | 1.0 | 362 | 0.4760 | 0.1920 | 0.0622 | 0.0739 | 0.0559 |
| 0.4104 | 2.0 | 724 | 0.4737 | 0.1912 | 0.0704 | 0.0688 | 0.0520 |
| 0.3848 | 3.0 | 1086 | 0.4567 | 0.1809 | 0.0595 | 0.0709 | 0.0504 |
| 0.3688 | 4.0 | 1448 | 0.4680 | 0.1831 | 0.0581 | 0.0738 | 0.0512 |
| 0.344 | 5.0 | 1810 | 0.4692 | 0.1840 | 0.0616 | 0.0711 | 0.0513 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1