wavlm_torgo_0H_1

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

• Loss: 4.4358
• Wer: 1.0

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: 0.0001
• train_batch_size: 1
• 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: 1000
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.6461	0.8365	2000	4.2106	1.0
3.5846	1.6729	4000	4.5378	1.0
3.563	2.5094	6000	4.9692	1.0
3.5338	3.3459	8000	4.5362	1.0
3.7176	4.1824	10000	4.3354	1.0
3.7041	5.0188	12000	4.4317	1.0
3.5544	5.8553	14000	4.3316	1.0
3.5242	6.6918	16000	4.4173	1.0
3.5293	7.5282	18000	4.4358	1.0

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1