medium
This model is a fine-tuned version of openai/whisper-medium.en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6406
- Wer: 10.0661
- Cer: 6.1253
- Wer Normalized: 10.0637
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: 32
- eval_batch_size: 16
- 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: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Wer Normalized |
|---|---|---|---|---|---|---|
| 0.4967 | 1.75 | 500 | 0.3843 | 9.3314 | 5.5994 | 9.3264 |
| 0.1883 | 3.51 | 1000 | 0.4699 | 9.8026 | 5.9139 | 9.7977 |
| 0.058 | 5.26 | 1500 | 0.6406 | 10.0661 | 6.1253 | 10.0637 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.12.1+cu116
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 74
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ImanNalia/medium
Base model
openai/whisper-medium.en