enhanced_german

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6891
• Accuracy: 0.6667

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.7047	0.3333
No log	2.0	2	0.6962	0.5
No log	3.0	3	0.6878	0.5833
No log	4.0	4	0.6962	0.6667
No log	5.0	5	0.6954	0.6667
No log	6.0	6	0.6951	0.5833
No log	7.0	7	0.6922	0.5833
No log	8.0	8	0.6907	0.5833
No log	9.0	9	0.6899	0.5833
0.3093	10.0	10	0.6891	0.6667

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1