Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Yoruba- Abdulhameed Dere
This model is a fine-tuned version of DereAbdulhameed/whisper-distill_large_v2_Yoruba on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8089
- Wer: 60.1043
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: 0.001
- train_batch_size: 3
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7515 | 1.0 | 906 | 0.8561 | 66.0174 |
| 0.4839 | 2.0 | 1812 | 0.8116 | 62.8323 |
| 0.1205 | 3.0 | 2718 | 0.8089 | 60.1043 |
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Unable to determine this model’s pipeline type. Check the
docs
.