---
license: apache-2.0
base_model: qanastek/whisper-small-french-uncased
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper_Fr_Ht
  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_Fr_Ht

This model is a fine-tuned version of [qanastek/whisper-small-french-uncased](https://huggingface.co/qanastek/whisper-small-french-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8968
- Wer: 1.0

## 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: 500
- training_steps: 4000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 0.293         | 3.95  | 1000 | 0.6567          | 1.0 |
| 0.0541        | 7.91  | 2000 | 0.7640          | 1.0 |
| 0.0063        | 11.86 | 3000 | 0.8664          | 1.0 |
| 0.0016        | 15.81 | 4000 | 0.8968          | 1.0 |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3