---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mst_2
  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. -->

# mst_2

This model is a fine-tuned version of [Sjdan/mst_1](https://huggingface.co/Sjdan/mst_1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0171
- Wer: 1.4486

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 3.3694        | 1.36  | 500  | 0.4818          | 1.7882 |
| 0.5491        | 2.72  | 1000 | 0.1489          | 1.5545 |
| 0.2598        | 4.09  | 1500 | 0.0206          | 1.1869 |
| 0.0938        | 5.45  | 2000 | 0.0436          | 1.5576 |
| 0.0549        | 6.81  | 2500 | 0.0171          | 1.4486 |


### Framework versions

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