---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-E10_freq_pause
  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-E10_freq_pause

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2920
- Cer: 28.2366

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 28.8751       | 0.1289 | 200  | 4.9115          | 100.0   |
| 5.0006        | 0.2579 | 400  | 4.7238          | 100.0   |
| 4.8671        | 0.3868 | 600  | 4.6553          | 100.0   |
| 4.823         | 0.5158 | 800  | 4.6273          | 100.0   |
| 4.7298        | 0.6447 | 1000 | 4.6856          | 100.0   |
| 4.6744        | 0.7737 | 1200 | 4.5653          | 99.2540 |
| 4.4414        | 0.9026 | 1400 | 4.3734          | 98.8781 |
| 3.5827        | 1.0316 | 1600 | 3.2674          | 59.4514 |
| 2.7774        | 1.1605 | 1800 | 2.6359          | 52.0089 |
| 2.3795        | 1.2895 | 2000 | 2.3016          | 43.4152 |
| 2.1081        | 1.4184 | 2200 | 2.0953          | 40.3783 |
| 1.9172        | 1.5474 | 2400 | 1.9540          | 37.8642 |
| 1.7123        | 1.6763 | 2600 | 1.7923          | 35.4382 |
| 1.5885        | 1.8053 | 2800 | 1.7213          | 35.2796 |
| 1.4393        | 1.9342 | 3000 | 1.5884          | 32.5247 |
| 1.3138        | 2.0632 | 3200 | 1.5391          | 32.6598 |
| 1.2288        | 2.1921 | 3400 | 1.4909          | 31.2794 |
| 1.1505        | 2.3211 | 3600 | 1.4126          | 30.3160 |
| 1.1316        | 2.4500 | 3800 | 1.4099          | 30.6743 |
| 1.0684        | 2.5790 | 4000 | 1.3603          | 28.8769 |
| 1.0779        | 2.7079 | 4200 | 1.3231          | 28.1896 |
| 1.0489        | 2.8369 | 4400 | 1.3002          | 28.3306 |
| 1.0278        | 2.9658 | 4600 | 1.2920          | 28.2366 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1