Whisper Large - Whisper with atco2-asr-atcosim
This model is a fine-tuned version of openai/whisper-large on the This is a dataset constructed from two datasets: ATCO2-ASR and ATCOSIM. dataset. It achieves the following results on the evaluation set:
- Loss: 0.0715
- Wer: 2.6422
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0547 | 1.9763 | 1000 | 0.0675 | 4.0346 |
| 0.0115 | 3.9526 | 2000 | 0.0690 | 2.8309 |
| 0.003 | 5.9289 | 3000 | 0.0682 | 2.6212 |
| 0.0003 | 7.9051 | 4000 | 0.0715 | 2.6422 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 74
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for youngsangroh/whisper-large-finetuned-atco2-asr-atcosim
Base model
openai/whisper-largeDataset used to train youngsangroh/whisper-large-finetuned-atco2-asr-atcosim
Evaluation results
- Wer on This is a dataset constructed from two datasets: ATCO2-ASR and ATCOSIM.self-reported2.642