<!-- 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. -->
base-model-fairseq-V1
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7644
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.8808 | 4.04 | 200 | 4.6158 |
3.8357 | 8.08 | 400 | 4.5245 |
3.7928 | 12.12 | 600 | 4.7469 |
3.874 | 16.16 | 800 | 4.6975 |
3.7893 | 20.2 | 1000 | 4.7110 |
3.8368 | 24.24 | 1200 | 4.8101 |
3.7922 | 28.28 | 1400 | 4.7443 |
3.7842 | 32.32 | 1600 | 4.8832 |
3.7882 | 36.36 | 1800 | 4.7598 |
3.7777 | 40.4 | 2000 | 4.8261 |
3.834 | 44.44 | 2200 | 4.7754 |
3.7972 | 48.48 | 2400 | 4.7644 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2