metadata
library_name: transformers
license: cc-by-sa-4.0
base_model: airesearch/wav2vec2-large-xlsr-53-th
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-large-xlsr-53-th-speech-emotion-recognition
results: []
wav2vec2-large-xlsr-53-th-speech-emotion-recognition
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: 0.8209
- Accuracy: 0.6849
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 |
|---|---|---|---|---|
| 1.4531 | 1.0 | 89 | 1.3187 | 0.4384 |
| 1.1932 | 2.0 | 178 | 1.1075 | 0.5416 |
| 0.984 | 3.0 | 267 | 0.9787 | 0.6024 |
| 0.9603 | 4.0 | 356 | 0.9281 | 0.6224 |
| 0.8789 | 5.0 | 445 | 0.9141 | 0.6361 |
| 0.9113 | 6.0 | 534 | 0.8611 | 0.6568 |
| 0.8453 | 7.0 | 623 | 0.8444 | 0.6656 |
| 0.7558 | 8.0 | 712 | 0.8257 | 0.6776 |
| 0.784 | 9.0 | 801 | 0.8341 | 0.6783 |
| 0.7566 | 10.0 | 890 | 0.8209 | 0.6849 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1