Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Medium
This model is a fine-tuned version of openai/whisper-medium on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.6490
- Wer: 30.7292
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: 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: 100
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.7546 | 0.2857 | 100 | 3.2105 | 63.0208 |
| 0.4356 | 0.5714 | 200 | 1.3116 | 36.4583 |
| 0.2571 | 0.8571 | 300 | 0.9753 | 33.8542 |
| 0.1775 | 1.1429 | 400 | 0.6774 | 30.2083 |
| 0.1434 | 1.4286 | 500 | 0.5962 | 29.6875 |
| 0.1428 | 1.7143 | 600 | 0.6490 | 30.7292 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for miosipof/ASR-Easycall-Whisper-v1
Base model
openai/whisper-medium