whisper-atcosim2
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0524
- Wer: 0.0304
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: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.5702 | 0.2 | 50 | 0.2557 | 0.1007 |
0.1181 | 0.39 | 100 | 0.1144 | 0.0775 |
0.1084 | 0.59 | 150 | 0.0747 | 0.0482 |
0.0737 | 0.79 | 200 | 0.0616 | 0.0369 |
0.064 | 0.98 | 250 | 0.0556 | 0.0440 |
0.0313 | 1.18 | 300 | 0.0524 | 0.0304 |
Framework versions
- Transformers 4.29.0
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.11.0
- Downloads last month
- 4
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.