---
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: 1.7494
- Wer: 1.0532

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 3.4828        | 2.8   | 2500  | 4.0554          | 1.7873 |
| 0.8683        | 5.61  | 5000  | 2.5401          | 1.3156 |
| 0.4394        | 8.41  | 7500  | 1.7519          | 1.1129 |
| 0.0497        | 11.21 | 10000 | 1.7102          | 1.0738 |
| 0.031         | 14.01 | 12500 | 1.7395          | 1.0512 |
| 0.0508        | 16.82 | 15000 | 1.7254          | 1.0463 |
| 0.0462        | 19.62 | 17500 | 1.7494          | 1.0532 |


### Framework versions

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