Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Uzbek STT
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1178
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: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.323 | 0.1650 | 500 | 2.0135 |
| 1.4141 | 0.3300 | 1000 | 1.2143 |
| 1.2739 | 0.4950 | 1500 | 1.1382 |
| 1.3098 | 0.6601 | 2000 | 1.1178 |
Framework versions
- PEFT 0.15.2.dev0
- Transformers 4.52.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 108
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for mustafoyev202/whisper-uz-adv
Base model
openai/whisper-large-v2