metadata
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_9_0
model-index:
- name: Whisper small zh - foriegn
results: []
Whisper small zh - foriegn
This model is a fine-tuned version of openai/whisper-small on the Common Voice 9 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2235
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2446 | 0.36 | 500 | 0.3424 |
| 0.3316 | 0.73 | 1000 | 0.3260 |
| 0.2777 | 1.09 | 1500 | 0.2939 |
| 0.1808 | 1.45 | 2000 | 0.2944 |
| 0.1822 | 1.82 | 2500 | 0.2589 |
| 0.1206 | 2.18 | 3000 | 0.2468 |
| 0.0715 | 2.54 | 3500 | 0.2319 |
| 0.0642 | 2.91 | 4000 | 0.2235 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0