---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: dys_asr_100h
  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. -->

# dys_asr_100h

This model is a fine-tuned version of [Splend1dchan/wav2vec2-large-100h-lv60-self](https://huggingface.co/Splend1dchan/wav2vec2-large-100h-lv60-self) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0362
- Wer: 1.0187

## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 10.8404       | 1.36  | 500  | 2.4671          | 1.0    |
| 1.7126        | 2.72  | 1000 | 0.3951          | 1.2118 |
| 0.5618        | 4.09  | 1500 | 0.1192          | 1.0841 |
| 0.2301        | 5.45  | 2000 | 0.0547          | 1.0187 |
| 0.1409        | 6.81  | 2500 | 0.0362          | 1.0187 |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2