metadata
language:
- es
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Large SEIN - COES SEIN - Version 4
results: []
Whisper Large SEIN - COES SEIN - Version 4
This model is a fine-tuned version of openai/whisper-large-v3 on the SEIN COES dataset. It achieves the following results on the evaluation set:
- Loss: 2.7037
- Wer: 116.0000
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: 16
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 1000.0 | 1000 | 2.4782 | 115.2727 |
| 0.0 | 2000.0 | 2000 | 2.6297 | 124.0 |
| 0.0 | 3000.0 | 3000 | 2.6806 | 113.8182 |
| 0.0 | 4000.0 | 4000 | 2.7037 | 116.0000 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1