<!-- 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. -->
distil-wav2vec2-finetuned-giga-speech
This model is a fine-tuned version of OthmaneJ/distil-wav2vec2 on the Giga Speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.4271
- Accuracy: 0.8882
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4425 | 1.0 | 1057 | 1.3045 | 0.5399 |
| 0.796 | 2.0 | 2114 | 0.8516 | 0.7284 |
| 0.9685 | 3.0 | 3171 | 0.5054 | 0.8626 |
| 0.5623 | 4.0 | 4228 | 0.4271 | 0.8882 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
