---
tags:
- generated_from_trainer
model-index:
- name: speaker-segmentation-fine-tuned-hindi
  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-hindi

This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2779
- Der: 0.0982
- False Alarm: 0.0135
- Missed Detection: 0.0243
- Confusion: 0.0604

## 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 | Der    | False Alarm | Missed Detection | Confusion |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
| 0.3532        | 1.0   | 219  | 0.3508          | 0.1126 | 0.0150      | 0.0270           | 0.0706    |
| 0.2898        | 2.0   | 438  | 0.3095          | 0.1061 | 0.0125      | 0.0277           | 0.0660    |
| 0.2481        | 3.0   | 657  | 0.2918          | 0.1048 | 0.0139      | 0.0253           | 0.0656    |
| 0.2393        | 4.0   | 876  | 0.2788          | 0.0986 | 0.0133      | 0.0246           | 0.0607    |
| 0.2504        | 5.0   | 1095 | 0.2779          | 0.0982 | 0.0135      | 0.0243           | 0.0604    |


### Framework versions

- Transformers 4.38.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.15.2