---
library_name: transformers
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
metrics:
- wer
- bleu
model-index:
- name: whisper-large-v3-turbo-FLEURS-GL-EN
  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-large-v3-turbo-FLEURS-GL-EN

This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0422
- Wer: 99.1150
- Bleu: 15.6996

## 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-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     | Bleu    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| 4.2758        | 1.0   | 5    | 3.8844          | 76.6962 | 17.9438 |
| 2.3967        | 2.0   | 10   | 2.6969          | 96.4602 | 13.4436 |
| 1.4928        | 3.0   | 15   | 2.2290          | 71.0914 | 19.0116 |
| 1.2668        | 4.0   | 20   | 2.0422          | 99.1150 | 15.6996 |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0