Edit model card

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
Downloads last month
1
Safetensors
Model size
94.6M params
Tensor type
F32
·

Finetuned from