<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_awesome_asr_mind_model_eval
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: 10.5160
- Wer: 0.9908
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
10.2688 | 100.0 | 500 | 10.4308 | 1.0 |
6.3563 | 200.0 | 1000 | 9.9089 | 1.0 |
4.1057 | 300.0 | 1500 | 8.2964 | 1.0 |
3.2326 | 400.0 | 2000 | 9.2519 | 1.0 |
2.873 | 500.0 | 2500 | 9.3622 | 1.0 |
2.4916 | 600.0 | 3000 | 9.2621 | 1.0 |
2.228 | 700.0 | 3500 | 9.9592 | 1.0 |
2.0444 | 800.0 | 4000 | 10.1934 | 0.9908 |
1.9349 | 900.0 | 4500 | 10.3290 | 0.9908 |
1.8857 | 1000.0 | 5000 | 10.5160 | 0.9908 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3