Whisper Large-v2 Marathi
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 mr dataset. It achieves the following results on the evaluation set:
- Loss: 0.3108
- Wer: 15.2206
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-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1931 | 3.04 | 200 | 0.2491 | 16.9270 |
| 0.1108 | 7.03 | 400 | 0.2379 | 15.2711 |
| 0.0548 | 11.02 | 600 | 0.2668 | 15.3120 |
| 0.0189 | 15.01 | 800 | 0.3108 | 15.2206 |
| 0.0078 | 18.05 | 1000 | 0.3499 | 15.5571 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2