metadata

language:
  - fr
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
base_model: openai/whisper-large-v2
model-index:
  - name: whisper-large-v2-french-2
    results: []

whisper-large-v2-french-2

This model is a fine-tuned version of openai/whisper-large-v2 on the COMMON_VOICE_13_0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.2931
eval_wer_ortho: 0.1809
eval_wer: 0.1322
eval_runtime: 19643.029
eval_samples_per_second: 0.82
eval_steps_per_second: 0.41
epoch: 2.0
step: 4190

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

Framework versions

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