metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-large
tags:
- generated_from_trainer
model-index:
- name: Whisper_e8eae673-8dea-4ce6-b9ac-7541bbcff1c8
results: []
Whisper_e8eae673-8dea-4ce6-b9ac-7541bbcff1c8
This model is a fine-tuned version of openai/whisper-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0833
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: 0.001
- train_batch_size: 8
- 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: 20
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3764 | 10.0 | 10 | 2.3759 |
| 0.7583 | 20.0 | 20 | 1.4695 |
| 8.3335 | 30.0 | 30 | 6.5259 |
| 6.1162 | 40.0 | 40 | 3.0373 |
| 0.468 | 50.0 | 50 | 2.0833 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1