metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_speach_model
results: []
my_awesome_speach_model
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9803
- Accuracy: 0.6923
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8889 | 6 | 0.8543 | 0.4615 |
| 0.3921 | 1.9259 | 13 | 1.0292 | 0.3846 |
| 0.4899 | 2.9630 | 20 | 0.7720 | 0.6923 |
| 0.4899 | 4.0 | 27 | 0.6074 | 0.6923 |
| 0.4529 | 4.8889 | 33 | 0.7270 | 0.6923 |
| 0.3684 | 5.9259 | 40 | 0.6883 | 0.6923 |
| 0.3684 | 6.9630 | 47 | 0.8489 | 0.6154 |
| 0.2618 | 8.0 | 54 | 0.8669 | 0.6154 |
| 0.2343 | 8.8889 | 60 | 0.9146 | 0.6923 |
| 0.2343 | 9.9259 | 67 | 0.8657 | 0.6154 |
| 0.2193 | 10.9630 | 74 | 0.6177 | 0.7692 |
| 0.2718 | 12.0 | 81 | 0.9329 | 0.5385 |
| 0.2718 | 12.8889 | 87 | 1.3075 | 0.5385 |
| 0.2549 | 13.9259 | 94 | 0.5816 | 0.8462 |
| 0.1191 | 14.9630 | 101 | 0.6591 | 0.7692 |
| 0.1191 | 16.0 | 108 | 0.7349 | 0.7692 |
| 0.1449 | 16.8889 | 114 | 0.9123 | 0.6923 |
| 0.0914 | 17.7778 | 120 | 0.9803 | 0.6923 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3