Whisper_Large_30_sent_ModelV2
This model is a fine-tuned version of openai/whisper-large on the 11 Sentences dataset. It achieves the following results on the evaluation set:
- Loss: 0.2239
- Wer: 5.0
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.7745 | 8.3333 | 50 | 1.2629 | 40.0 |
| 0.0301 | 16.6667 | 100 | 0.1945 | 5.0 |
| 0.0 | 25.0 | 150 | 0.2056 | 5.0 |
| 0.0 | 33.3333 | 200 | 0.2102 | 5.0 |
| 0.0 | 41.6667 | 250 | 0.2140 | 5.0 |
| 0.0 | 50.0 | 300 | 0.2172 | 5.0 |
| 0.0 | 58.3333 | 350 | 0.2198 | 5.0 |
| 0.0 | 66.6667 | 400 | 0.2220 | 5.0 |
| 0.0 | 75.0 | 450 | 0.2234 | 5.0 |
| 0.0 | 83.3333 | 500 | 0.2239 | 5.0 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 24
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 deepinfinityai/30_sentencesV2
Base model
openai/whisper-large