---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-sm-urdu-finetuned
  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. -->

# whisper-sm-urdu-finetuned

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [Common Voice 13.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_13_0/viewer/ur/train) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1777
- Wer: 36.0220

## 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: 1e-05
- train_batch_size: 16
- 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: 500
- training_steps: 4000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.4017        | 0.18  | 1000 | 0.2591          | 65.3388 |
| 0.3963        | 0.36  | 2000 | 0.2135          | 43.6355 |
| 0.3162        | 0.54  | 3000 | 0.1880          | 35.8573 |
| 0.3479        | 0.72  | 4000 | 0.1777          | 36.0220 |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3