Whisper openai-whisper-large
This model is a fine-tuned version of openai/whisper-large on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1954
- Wer: 40.5791
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: 2
- eval_batch_size: 1
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3338 | 2.6596 | 500 | 0.7921 | 42.5161 |
| 0.0335 | 5.3191 | 1000 | 0.9873 | 40.2465 |
| 0.0083 | 7.9787 | 1500 | 1.1470 | 40.3639 |
| 0.0007 | 10.6383 | 2000 | 1.1954 | 40.5791 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 21
Inference API (serverless) is not available, repository is disabled.
Model tree for DanielMarquez/openai-whisper-large-es_ecu911-2
Base model
openai/whisper-large
Finetuned
this model