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-jpn
results: []
speaker-segmentation-fine-tuned-callhome-jpn
This model is a fine-tuned version of pyannote/segmentation-3.0 on the diarizers-community/callhome jpn dataset. It achieves the following results on the evaluation set:
- Loss: 0.5957
- Der: 0.1975
- False Alarm: 0.0777
- Missed Detection: 0.0713
- Confusion: 0.0485
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 |
|---|---|---|---|---|---|---|---|
| 0.5998 | 1.0 | 336 | 0.6155 | 0.2067 | 0.0726 | 0.0792 | 0.0549 |
| 0.578 | 2.0 | 672 | 0.6258 | 0.2086 | 0.0851 | 0.0691 | 0.0544 |
| 0.5431 | 3.0 | 1008 | 0.6054 | 0.2023 | 0.0830 | 0.0689 | 0.0505 |
| 0.5198 | 4.0 | 1344 | 0.5989 | 0.1984 | 0.0762 | 0.0729 | 0.0494 |
| 0.5211 | 5.0 | 1680 | 0.5957 | 0.1975 | 0.0777 | 0.0713 | 0.0485 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1