---
library_name: transformers
language:
- id
license: mit
base_model: pyannote/speaker-diarization-3.1
tags:
- speaker-diarization
- speaker-segmentation
- modality:audio
- modality:text
- format:parquet
- generated_from_trainer
datasets:
- speaker-segmentation
model-index:
- name: speaker-segmentation-fine-tuned-id-2603
  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-id-2603

This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the speaker-segmentation dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7019
- Model Preparation Time: 0.0038
- Der: 0.2255
- False Alarm: 0.0699
- Missed Detection: 0.0388
- Confusion: 0.1168

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
| 0.7173        | 1.0   | 99   | 0.7460          | 0.0038                 | 0.2482 | 0.0758      | 0.0436           | 0.1288    |
| 0.6364        | 2.0   | 198  | 0.6885          | 0.0038                 | 0.2301 | 0.0710      | 0.0429           | 0.1162    |
| 0.5832        | 3.0   | 297  | 0.6896          | 0.0038                 | 0.2238 | 0.0717      | 0.0372           | 0.1149    |
| 0.5552        | 4.0   | 396  | 0.6964          | 0.0038                 | 0.2249 | 0.0700      | 0.0387           | 0.1162    |
| 0.5303        | 5.0   | 495  | 0.7019          | 0.0038                 | 0.2255 | 0.0699      | 0.0388           | 0.1168    |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1