---
library_name: transformers
language:
- bn
license: apache-2.0
base_model: google/umt5-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Elite_Enigmas/Version1
  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. -->

# Elite_Enigmas/Version1

This model is a fine-tuned version of [google/umt5-small](https://huggingface.co/google/umt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8451
- Wer: 1.1562

## 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: 0.0005
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 7.8432        | 4.0   | 4000 | 3.8762          | 1.0    |
| 3.0048        | 8.0   | 8000 | 2.8451          | 1.1562 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0