metadata
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-960h-fsc-h
results: []
wav2vec2-base-960h-fsc-h
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: 1.7220
- Accuracy: 0.2557
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: 0.0005
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9959 | 120 | 1.7220 | 0.2557 |
| No log | 2.0 | 241 | 1.7221 | 0.2557 |
| No log | 2.9959 | 361 | 1.7188 | 0.2557 |
| No log | 4.0 | 482 | 1.7197 | 0.2557 |
| No log | 4.9959 | 602 | 1.7183 | 0.2557 |
| No log | 6.0 | 723 | 1.7196 | 0.2557 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1