Downloads · 30 days
5
4% of all-time downloads
whisper-large-v2-basque-lr1e-5
Ansu/whisper-large-v2-basque-lr1e-5
whisper-large-v2-basque-lr1e-5 is a machine learning model from Ansu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
138
Public
Repo size
30.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 28, 2026
- Updated
- Jul 30, 2026
- SHA
- be755eda
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-basque-lr1e-5-freezeFalse
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1362
- Wer: 5.7138
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: 64
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1035 | 0.33 | 1000 | 0.1843 | 10.0599 |
| 0.0748 | 0.66 | 2000 | 0.1527 | 7.6496 |
| 0.0678 | 0.99 | 3000 | 0.1384 | 6.9439 |
| 0.0451 | 1.32 | 4000 | 0.1371 | 6.4319 |
| 0.0441 | 1.65 | 5000 | 0.1302 | 6.3007 |
| 0.0396 | 1.98 | 6000 | 0.1272 | 5.7824 |
| 0.0278 | 2.31 | 7000 | 0.1292 | 5.7637 |
| 0.0247 | 2.64 | 8000 | 0.1302 | 5.5576 |
| 0.0209 | 2.97 | 9000 | 0.1284 | 5.5701 |
| 0.0135 | 3.3 | 10000 | 0.1362 | 5.7138 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.3
- Type
- whisper
- License
- apache-2.0
- Created
- Jul 28, 2026
- Updated
- Jul 30, 2026