---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-sah
  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-sah

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: 0.4177
- Wer: 0.4480

## 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: 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: 1000
- num_epochs: 30

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.3675        | 4.5   | 500  | 2.2690          | 1.0    |
| 0.8695        | 9.01  | 1000 | 0.4878          | 0.5811 |
| 0.3469        | 13.51 | 1500 | 0.4021          | 0.4973 |
| 0.2236        | 18.02 | 2000 | 0.4299          | 0.4750 |
| 0.1685        | 22.52 | 2500 | 0.4266          | 0.4612 |
| 0.1383        | 27.03 | 3000 | 0.4177          | 0.4480 |


### Framework versions

- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3