whisper-base-finetuned
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0089
- Wer: 1.125
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.4641 | 0.2 | 10 | 0.2328 | 7.1250 |
0.1312 | 0.4 | 20 | 0.0801 | 4.0 |
0.0477 | 0.6 | 30 | 0.0390 | 2.25 |
0.0213 | 0.8 | 40 | 0.0232 | 1.875 |
0.0101 | 1.0 | 50 | 0.0157 | 1.875 |
0.0073 | 1.2 | 60 | 0.0126 | 1.25 |
0.0056 | 1.4 | 70 | 0.0109 | 1.25 |
0.005 | 1.6 | 80 | 0.0096 | 1.125 |
0.0048 | 1.8 | 90 | 0.0091 | 1.125 |
0.0049 | 2.0 | 100 | 0.0089 | 1.125 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.14.5
- Tokenizers 0.15.2
- Downloads last month
- 2
Inference API (serverless) is not available, repository is disabled.
Model tree for abbenedek/whisper-base-finetuned2
Base model
openai/whisper-base
Finetuned
this model