---
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-large-xlsr-53-english-finetuned-ravdess-v7
  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-large-xlsr-53-english-finetuned-ravdess-v7

This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8320
- Accuracy: 0.7986

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2518        | 0.15  | 25   | 1.0813          | 0.7222   |
| 0.4377        | 0.31  | 50   | 1.3678          | 0.6389   |
| 0.471         | 0.46  | 75   | 1.2841          | 0.6458   |
| 0.6906        | 0.62  | 100  | 1.0845          | 0.6736   |
| 0.8409        | 0.77  | 125  | 0.9987          | 0.7222   |
| 0.5912        | 0.93  | 150  | 0.9029          | 0.7292   |
| 0.6029        | 1.08  | 175  | 1.0862          | 0.6597   |
| 0.4525        | 1.23  | 200  | 1.0455          | 0.6806   |
| 0.4263        | 1.39  | 225  | 1.4209          | 0.6389   |
| 0.4866        | 1.54  | 250  | 1.0648          | 0.7222   |
| 0.3619        | 1.7   | 275  | 0.9949          | 0.7083   |
| 0.7256        | 1.85  | 300  | 1.1846          | 0.6875   |
| 0.3964        | 2.01  | 325  | 0.9130          | 0.7222   |
| 0.2853        | 2.16  | 350  | 1.0839          | 0.7292   |
| 0.3022        | 2.31  | 375  | 0.7729          | 0.7847   |
| 0.3631        | 2.47  | 400  | 1.2372          | 0.7153   |
| 0.3029        | 2.62  | 425  | 0.9880          | 0.7778   |
| 0.2665        | 2.78  | 450  | 1.1243          | 0.7569   |
| 0.2743        | 2.93  | 475  | 0.8395          | 0.7778   |
| 0.1787        | 3.09  | 500  | 0.8320          | 0.7986   |
| 0.1533        | 3.24  | 525  | 0.8909          | 0.7778   |
| 0.1636        | 3.4   | 550  | 1.1212          | 0.7569   |
| 0.1677        | 3.55  | 575  | 0.9527          | 0.7986   |
| 0.1166        | 3.7   | 600  | 0.9082          | 0.8056   |
| 0.1923        | 3.86  | 625  | 1.1074          | 0.75     |
| 0.108         | 4.01  | 650  | 1.0360          | 0.7847   |
| 0.1023        | 4.17  | 675  | 1.0964          | 0.7708   |
| 0.1122        | 4.32  | 700  | 1.2101          | 0.7569   |
| 0.1501        | 4.48  | 725  | 0.9138          | 0.8125   |
| 0.098         | 4.63  | 750  | 0.8422          | 0.8194   |
| 0.0585        | 4.78  | 775  | 1.0018          | 0.7917   |
| 0.1135        | 4.94  | 800  | 1.0409          | 0.7847   |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3