metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: wav2vec2-fluency-checkpoints
results: []
wav2vec2-fluency-checkpoints
This model is a fine-tuned version of facebook/wav2vec2-base-960h on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6840
- Accuracy: 0.24
- F1: 0.0484
- Qwk: 0.0
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
- optimizer: Use OptimizerNames.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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Qwk |
|---|---|---|---|---|---|---|
| 1.9027 | 1.0 | 149 | 1.5752 | 0.3919 | 0.0804 | 0.0 |
| 1.5771 | 2.0 | 298 | 1.5067 | 0.3919 | 0.0804 | 0.0 |
| 1.8437 | 3.0 | 447 | 1.5069 | 0.3919 | 0.0804 | 0.0 |
| 1.5636 | 4.0 | 596 | 1.5043 | 0.3919 | 0.0804 | 0.0 |
| 1.7911 | 5.0 | 745 | 1.5095 | 0.3919 | 0.0804 | 0.0 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1