metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: msc_imasc_openslr_festfox_Whisper_Medium_2
results: []
msc_imasc_openslr_festfox_Whisper_Medium_2
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0424
- Wer: 18.1637
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: 5e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0482 | 0.79 | 1000 | 0.0801 | 40.4827 |
| 0.0238 | 1.58 | 2000 | 0.0514 | 27.4944 |
| 0.0105 | 2.37 | 3000 | 0.0447 | 22.8415 |
| 0.0044 | 3.16 | 4000 | 0.0403 | 19.3580 |
| 0.0037 | 3.95 | 5000 | 0.0408 | 19.3083 |
| 0.0016 | 4.74 | 6000 | 0.0424 | 18.1637 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1