Whisper medium-translate Hi - Aa
This model is a fine-tuned version of Aakali/whisper-medium-hi on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9904
- Wer: 48.1161
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
---|---|---|---|---|
0.1405 | 2.4450 | 1000 | 0.7580 | 51.5075 |
0.0245 | 4.8900 | 2000 | 0.8571 | 51.4000 |
0.0026 | 7.3350 | 3000 | 0.9280 | 48.3132 |
0.0011 | 9.7800 | 4000 | 0.9673 | 47.6457 |
0.0006 | 12.2249 | 5000 | 0.9904 | 48.1161 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
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.