---
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: 1.2583
- Accuracy: 0.6597

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9468        | 0.15  | 25   | 1.0477          | 0.5833   |
| 0.9825        | 0.31  | 50   | 1.0943          | 0.5556   |
| 0.83          | 0.46  | 75   | 1.0094          | 0.6389   |
| 0.9219        | 0.62  | 100  | 1.1035          | 0.5833   |
| 0.9044        | 0.77  | 125  | 1.2343          | 0.5833   |
| 0.9362        | 0.93  | 150  | 1.2651          | 0.5972   |
| 0.8799        | 1.08  | 175  | 1.2690          | 0.5486   |
| 0.8219        | 1.23  | 200  | 1.1401          | 0.5764   |
| 0.7739        | 1.39  | 225  | 1.2107          | 0.5417   |
| 0.87          | 1.54  | 250  | 1.1299          | 0.6319   |
| 0.6298        | 1.7   | 275  | 0.9628          | 0.6736   |
| 0.5578        | 1.85  | 300  | 1.5402          | 0.5417   |
| 0.7363        | 2.01  | 325  | 1.0680          | 0.6667   |
| 0.5354        | 2.16  | 350  | 0.9104          | 0.6736   |
| 0.4246        | 2.31  | 375  | 0.9475          | 0.6667   |
| 0.479         | 2.47  | 400  | 1.2755          | 0.6597   |
| 0.5133        | 2.62  | 425  | 0.8993          | 0.7083   |
| 0.3661        | 2.78  | 450  | 1.0620          | 0.6667   |
| 0.3664        | 2.93  | 475  | 1.0617          | 0.6875   |
| 0.4177        | 3.09  | 500  | 1.2583          | 0.6597   |
| 0.4462        | 3.24  | 525  | 0.9819          | 0.7361   |
| 0.3419        | 3.4   | 550  | 1.2685          | 0.6667   |
| 0.5142        | 3.55  | 575  | 0.9290          | 0.75     |
| 0.2887        | 3.7   | 600  | 1.0275          | 0.7153   |
| 0.2485        | 3.86  | 625  | 0.7754          | 0.7778   |
| 0.3065        | 4.01  | 650  | 1.0046          | 0.7431   |
| 0.1812        | 4.17  | 675  | 0.9867          | 0.7361   |
| 0.1541        | 4.32  | 700  | 1.1906          | 0.6875   |
| 0.2993        | 4.48  | 725  | 0.9916          | 0.75     |
| 0.2149        | 4.63  | 750  | 1.0387          | 0.7222   |
| 0.1114        | 4.78  | 775  | 0.9461          | 0.7292   |
| 0.1897        | 4.94  | 800  | 0.9165          | 0.75     |


### Framework versions

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