---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
base_model: facebook/wav2vec2-xls-r-300m
model-index:
- name: wav2vec2-large-xls-r-300m-finetune-dali
  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-xls-r-300m-finetune-dali

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: 3.2332
- Wer: 0.7088

## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 9.1246        | 0.49  | 100  | 4.0976          | 1.0    |
| 4.5372        | 0.97  | 200  | 3.2580          | 1.0    |
| 3.2467        | 1.46  | 300  | 3.0922          | 1.0001 |
| 3.4683        | 1.94  | 400  | 2.7944          | 0.9588 |
| 2.56          | 2.43  | 500  | 2.7701          | 0.9228 |
| 3.5665        | 2.91  | 600  | 2.7017          | 0.9356 |
| 3.5163        | 3.4   | 700  | 2.6731          | 0.9019 |
| 2.7201        | 3.88  | 800  | 2.7024          | 0.9067 |
| 3.1927        | 4.37  | 900  | 2.7681          | 0.9083 |
| 2.6796        | 4.85  | 1000 | 2.6577          | 0.8902 |
| 2.7204        | 5.34  | 1100 | 2.5810          | 0.8899 |
| 2.8474        | 5.83  | 1200 | 2.6795          | 0.9008 |
| 3.4242        | 6.31  | 1300 | 2.5315          | 0.8699 |
| 2.6685        | 6.8   | 1400 | 2.6477          | 0.8743 |
| 2.8734        | 7.28  | 1500 | 2.6630          | 0.8772 |
| 3.0146        | 7.77  | 1600 | 2.5337          | 0.8667 |
| 2.1542        | 8.25  | 1700 | 2.5623          | 0.8345 |
| 2.8927        | 8.74  | 1800 | 2.4624          | 0.8185 |
| 2.4501        | 9.22  | 1900 | 2.5193          | 0.8196 |
| 2.5283        | 9.71  | 2000 | 2.5110          | 0.8231 |
| 2.7019        | 10.19 | 2100 | 2.5571          | 0.7776 |
| 1.8019        | 10.68 | 2200 | 2.4725          | 0.7735 |
| 1.8982        | 11.17 | 2300 | 2.5294          | 0.7662 |
| 1.553         | 11.65 | 2400 | 2.5773          | 0.7662 |
| 1.6364        | 12.14 | 2500 | 2.5883          | 0.7568 |
| 1.9175        | 12.62 | 2600 | 2.4496          | 0.7405 |
| 1.5186        | 13.11 | 2700 | 2.4917          | 0.7410 |
| 1.911         | 13.59 | 2800 | 2.4941          | 0.7280 |
| 1.389         | 14.08 | 2900 | 2.4738          | 0.7187 |
| 1.2499        | 14.56 | 3000 | 2.5277          | 0.7236 |
| 1.3069        | 15.05 | 3100 | 2.5051          | 0.7291 |
| 1.1218        | 15.53 | 3200 | 2.6532          | 0.7207 |
| 1.2423        | 16.02 | 3300 | 2.5690          | 0.7197 |
| 1.0828        | 16.5  | 3400 | 2.6145          | 0.7216 |
| 1.0926        | 16.99 | 3500 | 2.5524          | 0.7114 |
| 1.0012        | 17.48 | 3600 | 2.5685          | 0.7108 |
| 0.9849        | 17.96 | 3700 | 2.6362          | 0.7081 |
| 0.9141        | 18.45 | 3800 | 2.6395          | 0.7151 |
| 0.9115        | 18.93 | 3900 | 2.6901          | 0.7051 |
| 0.8355        | 19.42 | 4000 | 2.6799          | 0.7150 |
| 0.8134        | 19.9  | 4100 | 2.8110          | 0.7091 |
| 0.7593        | 20.39 | 4200 | 2.8204          | 0.7123 |
| 0.7528        | 20.87 | 4300 | 2.8369          | 0.7067 |
| 0.6899        | 21.36 | 4400 | 2.7883          | 0.7138 |
| 0.6799        | 21.84 | 4500 | 2.8745          | 0.7088 |
| 0.6268        | 22.33 | 4600 | 2.9128          | 0.7137 |
| 0.5877        | 22.82 | 4700 | 2.9422          | 0.7111 |
| 0.5789        | 23.3  | 4800 | 2.9755          | 0.7143 |
| 0.5338        | 23.79 | 4900 | 2.9797          | 0.7115 |
| 0.5143        | 24.27 | 5000 | 3.0170          | 0.7230 |
| 0.5019        | 24.76 | 5100 | 3.0441          | 0.7161 |
| 0.4791        | 25.24 | 5200 | 3.1360          | 0.7084 |
| 0.4557        | 25.73 | 5300 | 3.1516          | 0.7090 |
| 0.4293        | 26.21 | 5400 | 3.1535          | 0.7195 |
| 0.4116        | 26.7  | 5500 | 3.1685          | 0.7177 |
| 0.4108        | 27.18 | 5600 | 3.1756          | 0.7081 |
| 0.4012        | 27.67 | 5700 | 3.1828          | 0.7093 |
| 0.3753        | 28.16 | 5800 | 3.2102          | 0.7057 |
| 0.3605        | 28.64 | 5900 | 3.2137          | 0.7044 |
| 0.3678        | 29.13 | 6000 | 3.2202          | 0.7107 |
| 0.3541        | 29.61 | 6100 | 3.2332          | 0.7088 |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2