<!-- 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. -->
wav2vec2-base-timit-demo
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6519
- Cer: 0.1121
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.1338 | 8.0 | 500 | 0.5833 | 0.1592 |
| 0.4869 | 16.0 | 1000 | 0.3597 | 0.1123 |
| 0.2752 | 24.0 | 1500 | 0.4215 | 0.1161 |
| 0.1733 | 32.0 | 2000 | 0.5183 | 0.1120 |
| 0.1187 | 40.0 | 2500 | 0.6195 | 0.1138 |
| 0.0906 | 48.0 | 3000 | 0.6519 | 0.1121 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.13.3
