Downloads · 30 days
13
6% of all-time downloads
whisper-native-children-4-dutch
golesheed/whisper-native-children-4-dutch
whisper-native-children-4-dutch is a automatic speech recognition model from golesheed. 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
219
Public
Parameters
1.5B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 1, 2024
- Updated
- Feb 1, 2024
- SHA
- fc987f37
Base models
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 Large V2
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1557
- Wer: 5.4708
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: 3e-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: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4179 | 0.38 | 30 | 0.1898 | 8.5837 |
| 0.1742 | 0.75 | 60 | 0.1622 | 7.2374 |
| 0.1352 | 1.12 | 90 | 0.1535 | 6.1323 |
| 0.0757 | 1.5 | 120 | 0.1456 | 5.8288 |
| 0.0734 | 1.88 | 150 | 0.1496 | 5.9455 |
| 0.0488 | 2.25 | 180 | 0.1474 | 5.6965 |
| 0.0307 | 2.62 | 210 | 0.1475 | 5.8677 |
| 0.0303 | 3.0 | 240 | 0.1440 | 6.6770 |
| 0.0156 | 3.38 | 270 | 0.1498 | 5.2607 |
| 0.0133 | 3.75 | 300 | 0.1492 | 5.3541 |
| 0.0111 | 4.12 | 330 | 0.1504 | 5.4630 |
| 0.0063 | 4.5 | 360 | 0.1541 | 5.5175 |
| 0.0052 | 4.88 | 390 | 0.1557 | 5.4708 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- nl
- Created
- Feb 1, 2024
- Updated
- Feb 1, 2024