hf-audio-wav2vec2-bert-CV16-en-finetune
This model is a fine-tuned version of hf-audio/wav2vec2-bert-CV16-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3271
- Wer: 0.0879
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2428 | 1.4851 | 300 | 0.3659 | 0.1128 |
| 0.1906 | 2.9703 | 600 | 0.3201 | 0.0964 |
| 0.1250 | 4.4554 | 900 | 0.3123 | 0.0871 |
| 0.1418 | 5.9406 | 1200 | 0.3239 | 0.0840 |
| 0.1432 | 7.4257 | 1500 | 0.3621 | 0.0956 |
| 0.0693 | 8.9109 | 1800 | 0.3047 | 0.0855 |
| 0.1384 | 10.0 | 2020 | 0.3271 | 0.0879 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0
- Datasets 5.0.1
- Tokenizers 0.23.2