Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-sandi-train-dev-5
This model is a fine-tuned version of openai/whisper-large-v3 on the ntnu-smil/sandi2025-ds dataset. It achieves the following results on the evaluation set:
- Loss: 1.1667
- Wer: 155.1946
- Cer: 173.3475
- Decode Runtime: 302.3831
- Wer Runtime: 0.1938
- Cer Runtime: 0.4451
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: 7e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 28
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Decode Runtime | Wer Runtime | Cer Runtime |
|---|---|---|---|---|---|---|---|---|
| 3.1645 | 1.1435 | 7 | 1.6617 | 49.5816 | 236.5525 | 300.5728 | 0.1852 | 0.5012 |
| 1.4517 | 2.2870 | 14 | 1.3986 | 89.6658 | 230.5227 | 304.6352 | 0.1883 | 0.4913 |
| 1.2438 | 3.4305 | 21 | 1.2314 | 137.0728 | 210.6849 | 295.4402 | 0.1950 | 0.4713 |
| 1.1906 | 4.5740 | 28 | 1.1667 | 155.1946 | 173.3475 | 302.3831 | 0.1938 | 0.4451 |
Framework versions
- PEFT 0.15.1
- Transformers 4.48.3
- Pytorch 2.6.0
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The HF Inference API does not support automatic-speech-recognition models for peft
library.
Model tree for ntnu-smil/whisper-large-v3-sandi-train-dev-5
Base model
openai/whisper-large-v3