metadata
language:
- he
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Large V3 he ft - Chee Li
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Google Fleurs
type: google/fleurs
config: he_il
split: None
args: 'config: he split: test'
metrics:
- name: Wer
type: wer
value: 89.96973946416709
Whisper Large V3 he ft - Chee Li
This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.5137
- Wer: 89.9697
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-06
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1909 | 4.4643 | 1000 | 0.3820 | 74.8247 |
| 0.0604 | 8.9286 | 2000 | 0.4345 | 94.2210 |
| 0.0269 | 13.3929 | 3000 | 0.4905 | 96.9297 |
| 0.0119 | 17.8571 | 4000 | 0.5137 | 89.9697 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1