---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-hi2_test
  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-tiny-hi2_test

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5291
- Wer: 65.3061

## 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: 32
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 200
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 1.1886        | 1.25  | 40   | 0.9953          | 87.3910 |
| 0.6663        | 2.5   | 80   | 0.6781          | 73.2153 |
| 0.5053        | 3.75  | 120  | 0.5857          | 66.1783 |
| 0.406         | 5.0   | 160  | 0.5440          | 66.1106 |
| 0.3236        | 6.25  | 200  | 0.5291          | 65.3061 |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1