---
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-v6
  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-v6

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: 1.1552
- Accuracy: 0.5660

## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.079         | 0.07  | 10   | 2.0767          | 0.1667   |
| 2.0728        | 0.14  | 20   | 2.0719          | 0.1389   |
| 2.0713        | 0.21  | 30   | 2.0576          | 0.1562   |
| 2.056         | 0.28  | 40   | 2.0382          | 0.1181   |
| 2.0759        | 0.35  | 50   | 2.0160          | 0.2778   |
| 2.0117        | 0.42  | 60   | 1.9332          | 0.2778   |
| 1.8598        | 0.49  | 70   | 1.8759          | 0.2882   |
| 1.9277        | 0.56  | 80   | 1.8321          | 0.2812   |
| 1.7897        | 0.62  | 90   | 1.7278          | 0.3819   |
| 1.8157        | 0.69  | 100  | 1.7270          | 0.3646   |
| 1.9104        | 0.76  | 110  | 1.6997          | 0.3021   |
| 1.8557        | 0.83  | 120  | 1.6664          | 0.4271   |
| 1.8803        | 0.9   | 130  | 1.7943          | 0.3021   |
| 1.7548        | 0.97  | 140  | 1.8016          | 0.3021   |
| 1.7166        | 1.04  | 150  | 1.6303          | 0.3785   |
| 1.7237        | 1.11  | 160  | 1.6330          | 0.4132   |
| 1.7228        | 1.18  | 170  | 1.5905          | 0.4306   |
| 1.5683        | 1.25  | 180  | 1.5216          | 0.4340   |
| 1.716         | 1.32  | 190  | 1.4973          | 0.4306   |
| 1.562         | 1.39  | 200  | 1.5994          | 0.3715   |
| 1.5617        | 1.46  | 210  | 1.5699          | 0.4236   |
| 1.6539        | 1.53  | 220  | 1.5024          | 0.3993   |
| 1.58          | 1.6   | 230  | 1.4787          | 0.4132   |
| 1.5107        | 1.67  | 240  | 1.4252          | 0.4444   |
| 1.5934        | 1.74  | 250  | 1.4125          | 0.4444   |
| 1.54          | 1.81  | 260  | 1.4032          | 0.4236   |
| 1.4717        | 1.88  | 270  | 1.3636          | 0.4896   |
| 1.5257        | 1.94  | 280  | 1.5080          | 0.4306   |
| 1.4537        | 2.01  | 290  | 1.3346          | 0.4757   |
| 1.356         | 2.08  | 300  | 1.3636          | 0.4653   |
| 1.3572        | 2.15  | 310  | 1.3122          | 0.4757   |
| 1.2657        | 2.22  | 320  | 1.2927          | 0.5174   |
| 1.4931        | 2.29  | 330  | 1.3161          | 0.5382   |
| 1.3314        | 2.36  | 340  | 1.3248          | 0.5      |
| 1.375         | 2.43  | 350  | 1.2859          | 0.5521   |
| 1.3316        | 2.5   | 360  | 1.2747          | 0.5556   |
| 1.1443        | 2.57  | 370  | 1.2243          | 0.5625   |
| 1.3866        | 2.64  | 380  | 1.2122          | 0.5590   |
| 1.3274        | 2.71  | 390  | 1.2192          | 0.5174   |
| 1.1248        | 2.78  | 400  | 1.1993          | 0.5278   |
| 1.1337        | 2.85  | 410  | 1.1746          | 0.5556   |
| 1.1394        | 2.92  | 420  | 1.1603          | 0.5625   |
| 1.2199        | 2.99  | 430  | 1.1553          | 0.5660   |


### Framework versions

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