---
language:
- en
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
- h
- f
- '-'
- a
- s
- r
- l
- e
- d
- b
- o
metrics:
- wer
base_model: openai/whisper-tiny
model-index:
- name: Whisper Tiny English v2
  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 English v2

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the commands_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0003
- Wer: 3.3333

## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 300
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0098        | 1.0   | 75   | 0.0038          | 3.3333 |
| 0.0035        | 2.0   | 150  | 0.0006          | 3.75   |
| 0.0031        | 3.0   | 225  | 0.0004          | 3.1667 |
| 0.0012        | 4.0   | 300  | 0.0003          | 3.3333 |


### Framework versions

- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1