|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- kr |
|
|
license: mit |
|
|
base_model: pyannote/speaker-diarization-3.0 |
|
|
tags: |
|
|
- speaker-diarization |
|
|
- speaker-segmentation |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- test_data |
|
|
model-index: |
|
|
- name: speaker-segmentation-fine-tuned-korean3 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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-korean3 |
|
|
|
|
|
This model is a fine-tuned version of [pyannote/speaker-diarization-3.0](https://huggingface.co/pyannote/speaker-diarization-3.0) on the test_data dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1323 |
|
|
- Model Preparation Time: 0.0022 |
|
|
- Der: 0.0425 |
|
|
- False Alarm: 0.0014 |
|
|
- Missed Detection: 0.0007 |
|
|
- Confusion: 0.0404 |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch_fused 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:| |
|
|
| 0.1257 | 1.0 | 641 | 0.1864 | 0.0022 | 0.0767 | 0.0008 | 0.0019 | 0.0740 | |
|
|
| 0.0778 | 2.0 | 1282 | 0.2022 | 0.0022 | 0.0731 | 0.0011 | 0.0020 | 0.0701 | |
|
|
| 0.0995 | 3.0 | 1923 | 0.1758 | 0.0022 | 0.0716 | 0.0003 | 0.0031 | 0.0681 | |
|
|
| 0.0769 | 4.0 | 2564 | 0.1825 | 0.0022 | 0.0700 | 0.0004 | 0.0030 | 0.0666 | |
|
|
| 0.0855 | 5.0 | 3205 | 0.1790 | 0.0022 | 0.0704 | 0.0004 | 0.0030 | 0.0671 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.1 |
|
|
- Pytorch 2.9.1+cu128 |
|
|
- Datasets 4.4.1 |
|
|
- Tokenizers 0.22.1 |
|
|
|
