JSWOOK's picture
End of training
1731081 verified
---
library_name: transformers
language:
- en
license: mit
base_model: pyannote/speaker-diarization-3.1
tags:
- speaker-diarization
- speaker-segmentation
- generated_from_trainer
datasets:
- diarizers-community/voxconverse
model-index:
- name: JSWOOK/pyannote_2_finetuning
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. -->
# JSWOOK/pyannote_2_finetuning
This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the diarizers-community/voxconverse dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1327
- Model Preparation Time: 0.004
- Der: 0.0499
- False Alarm: 0.0304
- Missed Detection: 0.0094
- Confusion: 0.0101
## 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 | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
| No log | 1.0 | 21 | 0.1258 | 0.004 | 0.0486 | 0.0289 | 0.0104 | 0.0093 |
| 0.2277 | 2.0 | 42 | 0.1355 | 0.004 | 0.0509 | 0.0300 | 0.0097 | 0.0112 |
| 0.1872 | 3.0 | 63 | 0.1327 | 0.004 | 0.0494 | 0.0304 | 0.0095 | 0.0095 |
| 0.1649 | 4.0 | 84 | 0.1313 | 0.004 | 0.0492 | 0.0303 | 0.0094 | 0.0095 |
| 0.1535 | 5.0 | 105 | 0.1327 | 0.004 | 0.0499 | 0.0304 | 0.0094 | 0.0101 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1