metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- Japanese_english
metrics:
- wer
model-index:
- name: Whisper tiny Japanese
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Japanese English
type: Japanese_english
args: 'config: default, split: test'
metrics:
- name: Wer
type: wer
value: 22.274436090225564
Whisper tiny Japanese
This model is a fine-tuned version of openai/whisper-tiny on the Japanese English dataset. It achieves the following results on the evaluation set:
- Loss: 0.4847
- Wer: 22.2744
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1914 | 1.2438 | 1000 | 0.4866 | 22.9167 |
| 0.1464 | 2.4876 | 2000 | 0.4643 | 22.9010 |
| 0.0722 | 3.7313 | 3000 | 0.4761 | 21.9455 |
| 0.0503 | 4.9751 | 4000 | 0.4847 | 22.2744 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0