---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v2-base-pretrained_lr5e-5_at0.7_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_at0.7_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: 1.3723
- Wer: 0.1645

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 14.5862       | 4.46  | 250  | 3.6865          | 1.0    |
| 3.1591        | 8.93  | 500  | 3.2812          | 1.0    |
| 2.8713        | 13.39 | 750  | 2.2559          | 0.9658 |
| 0.7672        | 17.86 | 1000 | 0.7625          | 0.3093 |
| 0.216         | 22.32 | 1250 | 0.8197          | 0.2072 |
| 0.1328        | 26.79 | 1500 | 1.0511          | 0.1871 |
| 0.0963        | 31.25 | 1750 | 1.1082          | 0.1803 |
| 0.0808        | 35.71 | 2000 | 1.0651          | 0.1833 |
| 0.0681        | 40.18 | 2250 | 1.1422          | 0.1828 |
| 0.0631        | 44.64 | 2500 | 1.2823          | 0.1726 |
| 0.0573        | 49.11 | 2750 | 1.2592          | 0.1696 |
| 0.0528        | 53.57 | 3000 | 1.2268          | 0.1623 |
| 0.05          | 58.04 | 3250 | 1.2559          | 0.1674 |
| 0.0483        | 62.5  | 3500 | 1.2440          | 0.1700 |
| 0.0426        | 66.96 | 3750 | 1.3886          | 0.1713 |
| 0.0321        | 71.43 | 4000 | 1.3723          | 0.1645 |


### Framework versions

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