whisper-base-mixedv1.4
This model was trained from scratch on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3061
- Cer: 9.5109
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: 2
- 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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0363 | 8.85 | 1000 | 0.3010 | 10.1630 |
| 0.0003 | 17.7 | 2000 | 0.2905 | 9.1304 |
| 0.0003 | 26.55 | 3000 | 0.3068 | 9.0217 |
| 0.0001 | 35.4 | 4000 | 0.3061 | 9.5109 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.