metadata
language:
- fr
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper large v3 FR D&D - Joey Martig
results: []
Whisper large v3 FR D&D - Joey Martig
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1264
- Wer: 33.4454
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: 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: 50
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 7 | 1.0810 | 38.6555 |
| No log | 2.0 | 14 | 1.0631 | 38.7395 |
| No log | 3.0 | 21 | 0.9919 | 38.1513 |
| No log | 4.0 | 28 | 0.9135 | 37.3109 |
| No log | 5.0 | 35 | 0.7922 | 37.0588 |
| No log | 6.0 | 42 | 0.7013 | 35.6303 |
| No log | 7.0 | 49 | 0.6073 | 34.6218 |
| No log | 8.0 | 56 | 0.5099 | 45.5462 |
| No log | 9.0 | 63 | 0.4297 | 40.0 |
| No log | 10.0 | 70 | 0.3603 | 33.4454 |
| No log | 11.0 | 77 | 0.3024 | 33.4454 |
| No log | 12.0 | 84 | 0.2540 | 33.4454 |
| No log | 13.0 | 91 | 0.2196 | 33.4454 |
| No log | 14.0 | 98 | 0.1907 | 33.4454 |
| No log | 15.0 | 105 | 0.1695 | 36.7227 |
| No log | 16.0 | 112 | 0.1536 | 36.7227 |
| No log | 17.0 | 119 | 0.1421 | 33.4454 |
| No log | 18.0 | 126 | 0.1336 | 33.4454 |
| No log | 19.0 | 133 | 0.1282 | 33.4454 |
| No log | 20.0 | 140 | 0.1264 | 33.4454 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1