---
tags:
- generated_from_trainer
model-index:
- name: urdu_speech_tt
  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. -->

# urdu_speech_tt

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4909

## 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: 128
- eval_batch_size: 128
- 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: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5483        | 1.47  | 100  | 0.5064          |
| 0.5685        | 2.94  | 200  | 0.5075          |
| 0.5498        | 4.41  | 300  | 0.5030          |
| 0.5822        | 5.88  | 400  | 0.5036          |
| 0.5475        | 7.35  | 500  | 0.4987          |
| 0.5541        | 8.82  | 600  | 0.5001          |
| 0.5495        | 10.29 | 700  | 0.4949          |
| 0.5416        | 11.76 | 800  | 0.4925          |
| 0.5491        | 13.24 | 900  | 0.4922          |
| 0.5349        | 14.71 | 1000 | 0.4909          |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3