---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base.en
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-eng-transliterated-nep
  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-base-eng-transliterated-nep

This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co./openai/whisper-base.en) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6817
- Wer: 42.8102

## 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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 1.4867        | 3.0121 | 250  | 0.7501          | 50.5615 |
| 0.1176        | 6.0242 | 500  | 0.6817          | 42.8102 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0