metadata
library_name: transformers
language:
- jpn
license: mit
base_model: pyannote/speaker-diarization-3.1
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/speaker-diarization-3.1 on the diarizers-community/callhome dataset. It achieves the following results on the evaluation set:
- Loss: 0.7600
- Model Preparation Time: 0.0042
- Der: 0.2253
- False Alarm: 0.0463
- Missed Detection: 0.1355
- Confusion: 0.0434
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|---|
| 0.5792 | 1.0 | 328 | 0.7544 | 0.0042 | 0.2330 | 0.0530 | 0.1318 | 0.0482 |
| 0.5219 | 2.0 | 656 | 0.7515 | 0.0042 | 0.2265 | 0.0483 | 0.1352 | 0.0430 |
| 0.5221 | 3.0 | 984 | 0.7581 | 0.0042 | 0.2261 | 0.0489 | 0.1340 | 0.0432 |
| 0.5033 | 4.0 | 1312 | 0.7550 | 0.0042 | 0.2248 | 0.0489 | 0.1329 | 0.0429 |
| 0.5249 | 5.0 | 1640 | 0.7600 | 0.0042 | 0.2253 | 0.0463 | 0.1355 | 0.0434 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0