wav2vec2-large-xlsr-53-th-speech-emotion-recognition-3c-10ep

This model is a fine-tuned version of airesearch/wav2vec2-large-xlsr-53-th on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4026
• Accuracy: 0.8579

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: 3e-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
1.0361	0.9956	57	0.9022	0.6033
0.6365	1.9913	114	0.6374	0.7322
0.5076	2.9869	171	0.4952	0.7967
0.4822	4.0	229	0.4808	0.8098
0.4601	4.9956	286	0.4637	0.8306
0.3938	5.9913	343	0.4559	0.8317
0.365	6.9869	400	0.4052	0.8546
0.3498	8.0	458	0.3902	0.8590
0.3246	8.9956	515	0.4144	0.8546
0.3388	9.9563	570	0.4026	0.8579

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1