Whisper Small Odia
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 or dataset. It achieves the following results on the evaluation set:
- Loss: 0.4781
- Wer: 43.3568
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0628 | 12.01 | 250 | 0.2729 | 46.0649 |
| 0.0021 | 24.02 | 500 | 0.3792 | 59.7743 |
| 0.0004 | 37.01 | 750 | 0.4475 | 47.6728 |
| 0.0003 | 49.02 | 1000 | 0.4781 | 43.3568 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu102
- Datasets 2.10.0
- Tokenizers 0.13.2
- Downloads last month
- 2
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.
Dataset used to train chandan3007/Whisper-small-oriya
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 ortest set self-reported43.357