wav2vec2-large-xlsr-53-english-finetuned-ravdess-v8
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6533
- Accuracy: 0.7222
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1363 | 0.15 | 25 | 1.0081 | 0.7778 |
0.1327 | 0.31 | 50 | 0.9010 | 0.8125 |
0.1415 | 0.46 | 75 | 1.4153 | 0.7153 |
0.185 | 0.62 | 100 | 1.7617 | 0.7083 |
0.2158 | 0.77 | 125 | 2.1611 | 0.6597 |
0.4308 | 0.93 | 150 | 2.0827 | 0.6597 |
0.3191 | 1.08 | 175 | 2.2436 | 0.6319 |
0.3377 | 1.23 | 200 | 1.7225 | 0.6944 |
0.232 | 1.39 | 225 | 1.5759 | 0.7292 |
0.2571 | 1.54 | 250 | 1.8838 | 0.7222 |
0.2376 | 1.7 | 275 | 1.5548 | 0.7222 |
0.1417 | 1.85 | 300 | 1.2785 | 0.75 |
0.0731 | 2.01 | 325 | 1.4898 | 0.7431 |
0.0852 | 2.16 | 350 | 1.3757 | 0.75 |
0.0517 | 2.31 | 375 | 1.4918 | 0.7361 |
0.1537 | 2.47 | 400 | 1.4951 | 0.7431 |
0.0309 | 2.62 | 425 | 1.5893 | 0.7292 |
0.0021 | 2.78 | 450 | 1.6348 | 0.7292 |
0.0394 | 2.93 | 475 | 1.6533 | 0.7222 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.