---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: LISA_NOISE_TRAINED_MODEL
  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. -->

# LISA_NOISE_TRAINED_MODEL

This model is a fine-tuned version of [Shubham09/LISA_Whisper_small_latest](https://huggingface.co/Shubham09/LISA_Whisper_small_latest) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0786
- Wer: 161.6471

## 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: 8
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6605        | 7.14  | 50   | 1.0786          | 161.6471 |


### Framework versions

- Transformers 4.28.0.dev0
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2