README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: wav2vec2-base-finetuned-ks
    results: []

wav2vec2-base-finetuned-ks

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6810
• Accuracy: 0.6471

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 500
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	0.6810	0.6471
0.6835	2.0	10	0.6785	0.6471
0.6835	3.0	15	0.6748	0.6471
0.6745	4.0	20	0.6715	0.6471
0.6745	5.0	25	0.6688	0.6471
0.6773	6.0	30	0.6622	0.6471
0.6773	7.0	35	0.6585	0.6471
0.6663	8.0	40	0.6553	0.6471
0.6663	9.0	45	0.6539	0.6471
0.6254	10.0	50	0.6514	0.6471
0.6254	11.0	55	0.6506	0.6471
0.6697	12.0	60	0.6498	0.6471
0.6697	13.0	65	0.6604	0.6471
0.6485	14.0	70	0.6556	0.6471
0.6485	15.0	75	0.6504	0.6471
0.6802	16.0	80	0.6636	0.6471
0.6802	17.0	85	0.6521	0.6471
0.6737	18.0	90	0.6494	0.6471
0.6737	19.0	95	0.6494	0.6471
0.6687	20.0	100	0.6493	0.6471
0.6687	21.0	105	0.6500	0.6471
0.6456	22.0	110	0.6500	0.6471
0.6456	23.0	115	0.6493	0.6471
0.6448	24.0	120	0.6493	0.6471
0.6448	25.0	125	0.6495	0.6471

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2