juancopi81/whisper-medium-es
This model is a fine-tuned version of juancopi81/whisper-medium-es on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1893
- Wer: 5.9456
Using the script provided in the Whisper Sprint (Dec. 2022) the models achieves these results on the evaluation sets (WER):
- google/fleurs: 7.02
- mozilla-foundation/common_voice_11_0: XXXX
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: 32
- eval_batch_size: 16
- 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: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.244 | 1.01 | 1000 | 0.1848 | 6.4894 |
| 0.0714 | 2.02 | 2000 | 0.1805 | 5.9528 |
| 0.0285 | 3.03 | 3000 | 0.1893 | 5.9456 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.