---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v2-base-pretrained_lr5e-5_at0.8_da0.1
  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_at0.8_da0.1

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: 11.1145
- Wer: 0.8466

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 30.6579       | 50.0  | 250  | 9.9946          | 1.0    |
| 6.2256        | 100.0 | 500  | 8.2673          | 1.0    |
| 2.8836        | 150.0 | 750  | 8.1729          | 1.0    |
| 1.2163        | 200.0 | 1000 | 7.8384          | 1.0406 |
| 0.4153        | 250.0 | 1250 | 8.4861          | 0.9833 |
| 0.2165        | 300.0 | 1500 | 8.9662          | 0.9334 |
| 0.1446        | 350.0 | 1750 | 9.3884          | 0.8800 |
| 0.084         | 400.0 | 2000 | 9.8852          | 0.8898 |
| 0.0684        | 450.0 | 2250 | 10.0792         | 0.8988 |
| 0.0512        | 500.0 | 2500 | 10.3480         | 0.8548 |
| 0.0458        | 550.0 | 2750 | 10.6581         | 0.8855 |
| 0.0284        | 600.0 | 3000 | 10.6477         | 0.8800 |
| 0.0198        | 650.0 | 3250 | 10.7117         | 0.8642 |
| 0.0139        | 700.0 | 3500 | 11.0289         | 0.8595 |
| 0.0123        | 750.0 | 3750 | 11.1053         | 0.8432 |
| 0.0089        | 800.0 | 4000 | 11.1145         | 0.8466 |


### Framework versions

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