---
tags:
- generated_from_trainer
datasets:
- librispeech_asr
model-index:
- name: ''
  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. -->

# 

This model was trained from scratch on the librispeech_asr dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1277
- Wer: 1.0334

## 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: 0.0003
- 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: 3.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.7015        | 0.28  | 500  | 5.3313          | 1.9454 |
| 4.7239        | 0.56  | 1000 | 5.1316          | 1.9288 |
| 4.6686        | 0.84  | 1500 | 4.8812          | 1.9646 |
| 4.0138        | 1.12  | 2000 | 4.8274          | 1.8905 |
| 3.6314        | 1.4   | 2500 | 3.8913          | 1.7298 |
| 1.9511        | 1.68  | 3000 | 2.3486          | 1.3674 |
| 1.212         | 1.96  | 3500 | 1.6223          | 1.1877 |
| 0.8092        | 2.24  | 4000 | 1.3949          | 1.1049 |
| 0.497         | 2.52  | 4500 | 1.2544          | 1.0749 |
| 0.4401        | 2.8   | 5000 | 1.1277          | 1.0334 |


### Framework versions

- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0