---
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: wav2vec2-large-xlsr-53-urdu
  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. -->

# wav2vec2-large-xlsr-53-urdu

This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-urdu-urm-60](https://huggingface.co./Harveenchadha/vakyansh-wav2vec2-urdu-urm-60) on the common_voice dataset.
It achieves the following results on the evaluation set:
- Loss: 11.4593
- Wer: 0.5772
- Cer: 0.3384

## 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: 0.0003
- 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: 200
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 13.2136       | 8.33  | 100  | 9.5424          | 0.7672 | 0.4381 |
| 2.6996        | 16.67 | 200  | 8.4317          | 0.6661 | 0.3620 |
| 1.371         | 25.0  | 300  | 9.5518          | 0.6443 | 0.3701 |
| 0.639         | 33.33 | 400  | 9.4132          | 0.6129 | 0.3609 |
| 0.4452        | 41.67 | 500  | 10.8330         | 0.5920 | 0.3473 |
| 0.3233        | 50.0  | 600  | 11.4593         | 0.5772 | 0.3384 |


### Framework versions

- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3