FutureProofGlitch - Whisper Small - Version 2.0
This model is a fine-tuned version of futureProofGlitch/whisper-small on the Gigaspeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3078
- Wer Ortho: 28.4362
- Wer: 16.4524
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: 1.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2267 | 0.5 | 500 | 0.3309 | 29.5720 | 18.0966 |
| 0.2035 | 0.99 | 1000 | 0.3078 | 28.4362 | 16.4524 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 27
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.