whisper-medium-lozgen-female-model
This model is a fine-tuned version of openai/whisper-medium on the lozgen dataset. It achieves the following results on the evaluation set:
- Loss: 1.0600
- Wer: 0.4714
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch 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
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3322 | 3.4522 | 200 | 1.0600 | 0.4714 |
| 0.2339 | 6.9043 | 400 | 1.0910 | 0.5373 |
| 0.0724 | 10.3478 | 600 | 1.1510 | 0.4719 |
| 0.0284 | 13.8 | 800 | 1.2175 | 0.4074 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 3
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 csikasote/whisper-medium-lozgen-female-model
Base model
openai/whisper-medium