---
library_name: transformers
language:
- ha
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- eldad-akhaumere/common_voice_16_0_
metrics:
- bleu
model-index:
- name: Whisper Small_Ha Bleu - Eldad Akhaumere
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 16.0_
      type: eldad-akhaumere/common_voice_16_0_
      config: ha
      split: None
      args: 'config: ha, split: test'
    metrics:
    - name: Bleu
      type: bleu
      value: 11.764900582287524
---

<!-- 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 Small_Ha Bleu - Eldad Akhaumere

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.0_ dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8567
- Bleu: 11.7649

## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 1.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Bleu    |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.4391        | 0.3185 | 50   | 1.9226          | 7.4601  |
| 0.3422        | 0.6369 | 100  | 1.9320          | 9.7294  |
| 0.3862        | 0.9554 | 150  | 1.8567          | 11.7649 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4