metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: ft-wav2vec2-with-minds
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: minds14
type: minds14
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.11504424778761062
ft-wav2vec2-with-minds
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6358
- Accuracy: 0.1150
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 2.6358 | 0.1150 |
| No log | 2.0 | 4 | 2.6403 | 0.1062 |
| No log | 3.0 | 6 | 2.6474 | 0.0796 |
| No log | 4.0 | 8 | 2.6491 | 0.0442 |
| 2.6359 | 5.0 | 10 | 2.6499 | 0.0531 |
| 2.6359 | 6.0 | 12 | 2.6521 | 0.0531 |
| 2.6359 | 7.0 | 14 | 2.6526 | 0.0442 |
| 2.6359 | 8.0 | 16 | 2.6522 | 0.0354 |
| 2.6359 | 9.0 | 18 | 2.6520 | 0.0354 |
| 2.625 | 10.0 | 20 | 2.6521 | 0.0442 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0