---
license: mit
base_model: UmarRamzan/w2v2-bert-urdu
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v2-bert-urdu
  results: []
language:
- ur
---

<!-- 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. -->

# w2v2-bert-urdu

This model is a fine-tuned version of [UmarRamzan/w2v2-bert-urdu](https://huggingface.co/UmarRamzan/w2v2-bert-urdu) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3681
- Wer: 0.2929

## 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: 5e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 100
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.4362        | 0.1695 | 50   | 0.4144          | 0.3213 |
| 0.3776        | 0.3390 | 100  | 0.4029          | 0.3137 |
| 0.3918        | 0.5085 | 150  | 0.4095          | 0.3060 |
| 0.3968        | 0.6780 | 200  | 0.3961          | 0.3060 |
| 0.3685        | 0.8475 | 250  | 0.3681          | 0.2929 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1