Whisper Medium Mnong
This model is a fine-tuned version of openai/whisper-medium on the MnongAudio-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2759
- Wer: 20.7811
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 |
|---|---|---|---|---|
| 0.3667 | 2.0325 | 1000 | 0.5079 | 42.3819 |
| 0.0556 | 4.0650 | 2000 | 0.3091 | 24.1080 |
| 0.0089 | 6.0976 | 3000 | 0.2708 | 17.7917 |
| 0.0012 | 8.1301 | 4000 | 0.2759 | 20.7811 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.