---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- facebook/multilingual_librispeech
metrics:
- wer
model-index:
- name: Whisper medium French MLS
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: facebook/multilingual_librispeech French
      type: facebook/multilingual_librispeech
      config: french
      split: test
      args: french
    metrics:
    - name: Wer
      type: wer
      value: 6.497245494665325
---

<!-- 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 medium French MLS

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the facebook/multilingual_librispeech French dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1239
- Wer: 6.4972

## 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: 64
- eval_batch_size: 32
- 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: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.1424        | 1.0   | 1000 | 0.1239          | 6.4972 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2