metadata
library_name: transformers
language:
- zh
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper_largev3_motor_zh
results: []
Whisper_largev3_motor_zh
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1474
- Wer: 687.0393
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: 4
- 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: 100
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1996 | 0.0905 | 300 | 0.2141 | 335.3766 |
| 0.2683 | 0.1809 | 600 | 0.2006 | 354.0665 |
| 0.178 | 0.2714 | 900 | 0.1823 | 371.9752 |
| 0.0837 | 0.3619 | 1200 | 0.1587 | 1194.9519 |
| 0.0985 | 0.4524 | 1500 | 0.1474 | 687.0393 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3