---
library_name: transformers
language:
- fr
license: apache-2.0
base_model: StephaneBah/whisper-small-rad-fr1.1
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small Fr - Radiologie2.0 Encoder-Layer[0:3]+ LoRa(VO; FFN)
  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 Small Fr - Radiologie2.0 Encoder-Layer[0:3]+ LoRa(VO; FFN)

This model is a fine-tuned version of [StephaneBah/whisper-small-rad-fr1.1](https://huggingface.co/StephaneBah/whisper-small-rad-fr1.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8274
- Wer: 34.4912

## 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: 8
- eval_batch_size: 6
- seed: 3407
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log        | 6.25  | 100  | 0.8132          | 34.6130 |
| No log        | 12.5  | 200  | 0.8152          | 34.3083 |
| No log        | 18.75 | 300  | 0.8176          | 34.6740 |
| No log        | 25.0  | 400  | 0.8215          | 34.3083 |
| 0.0001        | 31.25 | 500  | 0.8223          | 34.5521 |
| 0.0001        | 37.5  | 600  | 0.8245          | 34.5521 |
| 0.0001        | 43.75 | 700  | 0.8261          | 34.4912 |
| 0.0001        | 50.0  | 800  | 0.8273          | 34.4912 |
| 0.0001        | 56.25 | 900  | 0.8268          | 34.4912 |
| 0.0           | 62.5  | 1000 | 0.8274          | 34.4912 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2