Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
LoRA-Frisian-1h
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_6_1 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0671
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: 0.0001
- train_batch_size: 8
- 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: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6832 | 1.0 | 89 | 2.2969 |
| 1.7271 | 2.0 | 178 | 1.8073 |
| 1.1859 | 3.0 | 267 | 1.2185 |
| 0.8731 | 4.0 | 356 | 1.1368 |
| 0.6939 | 5.0 | 445 | 1.0880 |
| 0.5879 | 6.0 | 534 | 1.0747 |
| 0.5184 | 7.0 | 623 | 1.0622 |
| 0.4325 | 8.0 | 712 | 1.0624 |
| 0.4024 | 9.0 | 801 | 1.0610 |
| 0.3826 | 10.0 | 890 | 1.0671 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 7
Model tree for xuliu15/Frisian_32r_LoRA_1h_new
Base model
openai/whisper-small