resultsfinal

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6727
• Accuracy: 0.6180

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: 0.005
• 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: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7409	1.0	23	0.7039	0.6180
0.696	2.0	46	0.6730	0.6180
0.6814	3.0	69	0.6656	0.6180
0.6928	4.0	92	0.6776	0.6180
0.7039	5.0	115	0.6706	0.6180
0.6963	6.0	138	0.6704	0.6180
0.7109	7.0	161	0.6724	0.6180
0.7048	8.0	184	0.6678	0.6180
0.6897	9.0	207	0.6745	0.6180
0.694	10.0	230	0.6742	0.6180
0.6761	11.0	253	0.6704	0.6180
0.6856	12.0	276	0.6666	0.6180
0.6796	13.0	299	0.6720	0.6180
0.7024	14.0	322	0.6738	0.6180
0.68	15.0	345	0.6721	0.6180
0.6799	16.0	368	0.6696	0.6180
0.6912	17.0	391	0.6727	0.6180
0.6896	18.0	414	0.6735	0.6180
0.6856	19.0	437	0.6731	0.6180
0.6753	20.0	460	0.6727	0.6180

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3