---
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
model-index:
- name: bambara-asr-v4
  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. -->

# bambara-asr-v4

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6734

## 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: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.9052        | 1.0    | 1708  | 0.9113          |
| 0.8135        | 2.0    | 3416  | 0.8085          |
| 0.762         | 3.0    | 5124  | 0.7595          |
| 0.728         | 4.0    | 6832  | 0.7322          |
| 0.6884        | 5.0    | 8540  | 0.7113          |
| 0.6784        | 6.0    | 10248 | 0.6970          |
| 0.6616        | 7.0    | 11956 | 0.6868          |
| 0.679         | 8.0    | 13664 | 0.6789          |
| 0.6574        | 9.0    | 15372 | 0.6754          |
| 0.6217        | 9.9946 | 17070 | 0.6734          |


### Framework versions

- PEFT 0.14.1.dev0
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0