joeyMartig/test-small-dnd-fr

Test Small FR DnD - Joey Martig

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0796
• Wer: 74.7059

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	7	1.4690	51.0924
No log	2.0	14	1.2158	47.1429
No log	3.0	21	0.9747	43.6975
No log	4.0	28	0.7241	35.2941
No log	5.0	35	0.4766	91.5126
No log	6.0	42	0.3080	97.8151
No log	7.0	49	0.1937	78.2353
No log	8.0	56	0.1173	78.2353
No log	9.0	63	0.0884	73.4454
No log	10.0	70	0.0796	74.7059

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1