metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: whisper-small-chinese-tw-minnan
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: nan-tw
split: test
args: nan-tw
metrics:
- name: Wer
type: wer
value: 96.9298245614035
whisper-small-chinese-tw-minnan
This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1626
- Wer: 96.9298
- Cer: 30.1452
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | Wer | Cer |
|---|---|---|---|---|---|
| 0.106 | 3.6364 | 1000 | 0.8017 | 110.0877 | 37.4445 |
| 0.0094 | 7.2727 | 2000 | 0.9844 | 101.9424 | 37.1209 |
| 0.0007 | 10.9091 | 3000 | 1.0714 | 95.8020 | 31.5374 |
| 0.0002 | 14.5455 | 4000 | 1.1310 | 96.0526 | 29.5809 |
| 0.0001 | 18.1818 | 5000 | 1.1626 | 96.9298 | 30.1452 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3