tmp
This model is a fine-tuned version of facebook/wav2vec2-base on the speech_commands dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.5422
- eval_accuracy: 0.8916
- eval_f1: 0.8835
- eval_runtime: 7.8567
- eval_samples_per_second: 392.147
- eval_steps_per_second: 1.655
- epoch: 4.0423
- step: 861
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: 240
- eval_batch_size: 240
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 3
Model tree for Zarakun/tmp
Base model
facebook/wav2vec2-base