Whisper tiny Greek El Greco
This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_11_0 el dataset. It achieves the following results on the evaluation set:
- Loss: 0.5615
- Wer: 45.6538
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: 3e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3389 | 8.33 | 1000 | 0.5659 | 49.1363 |
| 0.1562 | 16.67 | 2000 | 0.5615 | 45.6538 |
| 0.0616 | 25.0 | 3000 | 0.6440 | 46.9632 |
| 0.0116 | 33.33 | 4000 | 0.7578 | 47.9569 |
| 0.0046 | 41.67 | 5000 | 0.8374 | 48.6999 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 2.0.0.dev20221216+cu116
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 13
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.
Dataset used to train emilios/whisper-tn-el-e1
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 elself-reported45.654