|
--- |
|
license: mit |
|
base_model: pyannote/segmentation-3.0 |
|
tags: |
|
- speaker-diarization |
|
- speaker-segmentation |
|
- generated_from_trainer |
|
datasets: |
|
- KMayanja/backup_uganda |
|
model-index: |
|
- name: speaker-segmentation-fine-tuned-backup-uganda |
|
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-backup-uganda |
|
|
|
This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the KMayanja/backup_uganda default dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2271 |
|
- Der: 0.0667 |
|
- False Alarm: 0.0188 |
|
- Missed Detection: 0.0260 |
|
- Confusion: 0.0219 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:| |
|
| 0.1819 | 1.0 | 266 | 0.2174 | 0.0663 | 0.0186 | 0.0249 | 0.0228 | |
|
| 0.1659 | 2.0 | 532 | 0.2177 | 0.0669 | 0.0169 | 0.0278 | 0.0221 | |
|
| 0.1549 | 3.0 | 798 | 0.2170 | 0.0659 | 0.0181 | 0.0261 | 0.0217 | |
|
| 0.1535 | 4.0 | 1064 | 0.2222 | 0.0666 | 0.0195 | 0.0251 | 0.0220 | |
|
| 0.1541 | 5.0 | 1330 | 0.2271 | 0.0667 | 0.0188 | 0.0260 | 0.0219 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
