Downloads · 30 days
8
0% of all-time downloads
whisper-small-portuguese-1
Berly00/whisper-small-portuguese-1
whisper-small-portuguese-1 is a automatic speech recognition model from Berly00. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
2.1K
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 24, 2024
- Updated
- Jul 24, 2024
- SHA
- 41a5f410
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper small pt - m1
This model is a fine-tuned version of openai/whisper-small on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2815
- Wer: 8.9935
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: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0892 | 2.8571 | 500 | 0.2241 | 8.9747 |
| 0.0041 | 5.7143 | 1000 | 0.2586 | 8.9653 |
| 0.0014 | 8.5714 | 1500 | 0.2702 | 8.8665 |
| 0.001 | 11.4286 | 2000 | 0.2788 | 8.9512 |
| 0.0008 | 14.2857 | 2500 | 0.2815 | 8.9935 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- pt
- Created
- Jul 24, 2024
- Updated
- Jul 24, 2024