metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
model-index:
- name: whisper-base-yue-hk-mdccl
results: []
whisper-base-yue-hk-mdccl
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3399
- Cer: 17.7311
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.217 | 3.55 | 1000 | 0.3253 | 16.2053 |
| 0.0911 | 7.1 | 2000 | 0.3196 | 16.5350 |
| 0.0463 | 10.66 | 3000 | 0.3399 | 17.7311 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1