---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v2-base-pretrained_lr5e-5_at0.0_da1
  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. -->

# w2v2-base-pretrained_lr5e-5_at0.0_da1

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0838
- Wer: 0.1768

## 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: 5e-05
- train_batch_size: 32
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 16.3345       | 3.91  | 250  | 3.9551          | 1.0    |
| 3.2558        | 7.81  | 500  | 3.1516          | 1.0    |
| 2.9971        | 11.72 | 750  | 2.4403          | 1.0    |
| 0.9923        | 15.62 | 1000 | 0.6040          | 0.4938 |
| 0.2971        | 19.53 | 1250 | 0.6870          | 0.2828 |
| 0.1765        | 23.44 | 1500 | 0.8956          | 0.2431 |
| 0.1185        | 27.34 | 1750 | 0.9472          | 0.2029 |
| 0.0919        | 31.25 | 2000 | 1.0306          | 0.1833 |
| 0.0692        | 35.16 | 2250 | 0.9844          | 0.1939 |
| 0.0577        | 39.06 | 2500 | 1.0122          | 0.1862 |
| 0.0467        | 42.97 | 2750 | 1.0849          | 0.1734 |
| 0.0407        | 46.88 | 3000 | 0.9989          | 0.1841 |
| 0.0341        | 50.78 | 3250 | 1.0820          | 0.1875 |
| 0.0299        | 54.69 | 3500 | 1.1344          | 0.1747 |
| 0.0291        | 58.59 | 3750 | 1.0495          | 0.1845 |
| 0.0247        | 62.5  | 4000 | 1.0838          | 0.1768 |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.14.6
- Tokenizers 0.14.1