---
language:
- he
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: he
  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. -->

# he

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4955
- Wer: 81.1538

## 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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 300
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.8944        | 2.27  | 50   | 1.3441          | 106.9231 |
| 0.9601        | 4.55  | 100  | 0.7752          | 104.2308 |
| 0.5514        | 6.82  | 150  | 0.5895          | 100.5128 |
| 0.3454        | 9.09  | 200  | 0.5149          | 97.1795  |
| 0.1951        | 11.36 | 250  | 0.4918          | 83.4615  |
| 0.1149        | 13.64 | 300  | 0.4955          | 81.1538  |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1