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: 0.0117
- 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-05
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 7 | 0.9825 | 38.1513 |
| No log | 2.0 | 14 | 0.7112 | 35.7143 |
| No log | 3.0 | 21 | 0.4668 | 68.2353 |
| No log | 4.0 | 28 | 0.2396 | 33.6134 |
| No log | 5.0 | 35 | 0.1178 | 33.4454 |
| No log | 6.0 | 42 | 0.0526 | 33.4454 |
| No log | 7.0 | 49 | 0.0317 | 33.4454 |
| No log | 8.0 | 56 | 0.0165 | 33.4454 |
| No log | 9.0 | 63 | 0.0133 | 33.4454 |
| No log | 10.0 | 70 | 0.0117 | 33.4454 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1