Whisper Small Uzbek
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 uz dataset. It achieves the following results on the evaluation set:
- Loss: 0.4357
- Wer: 25.7857
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: 16
- 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: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3621 | 1.03 | 1000 | 0.4819 | 32.3209 |
| 0.2378 | 2.07 | 2000 | 0.4413 | 29.0077 |
| 0.2342 | 4.01 | 3000 | 0.4224 | 27.3939 |
| 0.1286 | 5.04 | 4000 | 0.4357 | 25.7857 |
| 0.1192 | 6.08 | 5000 | 0.4727 | 27.2752 |
| 0.0147 | 8.02 | 6000 | 0.5230 | 26.7267 |
| 0.0425 | 9.05 | 7000 | 0.5336 | 26.3628 |
| 0.0059 | 10.08 | 8000 | 0.5658 | 26.8476 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 8
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 shivkumarganesh/whisper-small-uz-v1
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 uztest set self-reported25.786