metadata

language:
  - fr
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
metrics:
  - wer
model-index:
  - name: whisper-large-v2-french
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: VOXPOPULI
          type: facebook/voxpopuli
          config: fr
          split: test
          args: fr
        metrics:
          - name: Wer
            type: wer
            value: 0.10414829788606697

whisper-large-v2-french

This model is a fine-tuned version of openai/whisper-large-v2 on the VOXPOPULI dataset. It achieves the following results on the evaluation set:

Loss: 0.2468
Wer Ortho: 0.1405
Wer: 0.1041

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1851	1.0	2207	0.2349	0.1399	0.1044
0.1318	2.0	4415	0.2312	0.1377	0.1015
0.0921	3.0	6621	0.2468	0.1405	0.1041

Framework versions

Transformers 4.30.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3