---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-iemocap
  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. -->

# wav2vec2-base-finetuned-iemocap

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9498
- Accuracy: 0.6799

## 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: 2e-05
- 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: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.2595        | 1.0   | 139  | 1.2167          | 0.4177   |
| 1.0205        | 2.0   | 278  | 0.9921          | 0.5823   |
| 0.8923        | 3.0   | 417  | 0.9213          | 0.6040   |
| 0.7682        | 4.0   | 556  | 1.0543          | 0.5895   |
| 0.6554        | 5.0   | 695  | 0.9086          | 0.6420   |
| 0.5389        | 6.0   | 834  | 0.8520          | 0.6817   |
| 0.4351        | 7.0   | 973  | 0.9517          | 0.6745   |
| 0.3707        | 8.0   | 1112 | 0.8934          | 0.6908   |
| 0.3057        | 9.0   | 1251 | 0.9342          | 0.6781   |
| 0.2566        | 10.0  | 1390 | 0.9498          | 0.6799   |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1