---
library_name: transformers
language:
- fr
license: mit
base_model: bofenghuang/whisper-large-v3-french
tags:
- generated_from_trainer
datasets:
- PraxySante/PxCorpus-PxSLU
- PraxySante/MediaSpeech
- BrunoHays/multilingual-TEDX-fr
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Large v3 French PraxySante - Fine-tuned
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: PxCorpus PxSLU
      type: PraxySante/PxCorpus-PxSLU
      args: 'config: fr, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 27.715877437325904
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: MediaSpeech
      type: PraxySante/MediaSpeech
    metrics:
    - name: Wer
      type: wer
      value: 27.715877437325904
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Multilingual TedX Fr
      type: BrunoHays/multilingual-TEDX-fr
    metrics:
    - name: Wer
      type: wer
      value: 27.715877437325904
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17
      type: mozilla-foundation/common_voice_17_0
    metrics:
    - name: Wer
      type: wer
      value: 27.715877437325904
---

<!-- 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 Large v3 French PraxySante - Fine-tuned

This model is a fine-tuned version of [bofenghuang/whisper-large-v3-french](https://huggingface.co/bofenghuang/whisper-large-v3-french) on the PxCorpus PxSLU, the MediaSpeech, the Multilingual TedX Fr and the Common Voice 17 datasets.
It achieves the following results on the evaluation set:
- Loss: 0.6630
- Wer: 27.7159

## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.5569        | 1.6129 | 25   | 0.6630          | 27.7159 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.3.0
- Datasets 2.21.0
- Tokenizers 0.19.1