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