metadata
language:
- cn
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- Svetlana0303/my_CN_ds
metrics:
- wer
model-index:
- name: Whisper Small CN - my voice
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: my_CN_ds
type: Svetlana0303/my_CN_ds
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 100
Whisper Small CN - my voice
This model is a fine-tuned version of openai/whisper-small on the my_CN_ds dataset. It achieves the following results on the evaluation set:
- Loss: 0.7879
- Wer: 100.0
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: 16
- 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: 50
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 100.0 | 100 | 0.7750 | 100.0 |
| 0.0 | 200.0 | 200 | 0.7819 | 100.0 |
| 0.0 | 300.0 | 300 | 0.7860 | 100.0 |
| 0.0 | 400.0 | 400 | 0.7879 | 100.0 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1