FILALIHicham/whisper-large-v3-fr-pxcorpus

Whisper Large v3 French PxCorpus - Fine-tuning test

This model is a fine-tuned version of bofenghuang/whisper-large-v3-french on the PxCorpus PxSLU dataset. It achieves the following results on the evaluation set:

• Loss: 0.1903
• Wer: 4.1126

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: 16
• eval_batch_size: 8
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0016	8.1967	1000	0.1864	5.1948
0.0003	16.3934	2000	0.1773	5.1948
0.0001	24.5902	3000	0.1860	4.1126
0.0	32.7869	4000	0.1903	4.1126

Framework versions

• Transformers 4.44.1
• Pytorch 2.4.0+cu124
• Datasets 2.21.0
• Tokenizers 0.19.1