metadata
language:
- ja
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
metrics:
- wer
model-index:
- name: whisper-large-v3-japanese-4k-steps
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 16.1
type: mozilla-foundation/common_voice_16_1
config: ja
split: None
args: 'config: ja, split: test'
metrics:
- name: Wer
type: wer
value: 1821.4909443725744
whisper-large-v3-japanese-4k-steps
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4057
- Wer: 1821.4909
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1374 | 1.02 | 1000 | 0.3618 | 1198.3182 |
| 0.0508 | 2.04 | 2000 | 0.3658 | 1755.4657 |
| 0.0206 | 3.05 | 3000 | 0.3904 | 2108.7484 |
| 0.0066 | 4.07 | 4000 | 0.4057 | 1821.4909 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2