metadata
language:
- vi
base_model: openai/whisper-medium-ja-v2
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Medium Vi - Anh Phuong
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: ja
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 62.82245827010622
Whisper Medium Vi - Anh Phuong
This model is a fine-tuned version of openai/whisper-medium-ja-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3098
- Wer: 62.8225
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1131 | 1.4556 | 1000 | 0.2257 | 68.5454 |
| 0.0579 | 2.9112 | 2000 | 0.2363 | 65.5105 |
| 0.0087 | 4.3668 | 3000 | 0.2685 | 65.1203 |
| 0.003 | 5.8224 | 4000 | 0.2924 | 63.9931 |
| 0.0007 | 7.2780 | 5000 | 0.3041 | 63.1043 |
| 0.0005 | 8.7336 | 6000 | 0.3098 | 62.8225 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1