|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base-960h |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-large-xlsr-quality-daps |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# wav2vec2-large-xlsr-quality-daps |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0289 |
|
- Accuracy: 0.9956 |
|
|
|
## 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: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 512 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| 0.6868 | 0.9630 | 13 | 0.6218 | 0.9595 | |
|
| 0.6219 | 2.0 | 27 | 0.3568 | 0.9947 | |
|
| 0.2823 | 2.9630 | 40 | 0.1729 | 0.9947 | |
|
| 0.1789 | 4.0 | 54 | 0.0902 | 0.9947 | |
|
| 0.1154 | 4.9630 | 67 | 0.0586 | 0.9952 | |
|
| 0.063 | 6.0 | 81 | 0.0421 | 0.9960 | |
|
| 0.0412 | 6.9630 | 94 | 0.0357 | 0.9960 | |
|
| 0.0412 | 8.0 | 108 | 0.0395 | 0.9934 | |
|
| 0.0376 | 8.9630 | 121 | 0.0312 | 0.9956 | |
|
| 0.0248 | 10.0 | 135 | 0.0296 | 0.9960 | |
|
| 0.0384 | 10.9630 | 148 | 0.0298 | 0.9952 | |
|
| 0.0267 | 12.0 | 162 | 0.0319 | 0.9943 | |
|
| 0.0244 | 12.9630 | 175 | 0.0307 | 0.9947 | |
|
| 0.0197 | 14.0 | 189 | 0.0289 | 0.9956 | |
|
| 0.023 | 14.4444 | 195 | 0.0289 | 0.9956 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.19.1 |
|
|
