Downloads · 30 days
4
0% of all-time downloads
irish-whisper-combined-aug
Eimhin03/irish-whisper-combined-aug
irish-whisper-combined-aug is a automatic speech recognition model from Eimhin03. 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
1.2K
Public
Parameters
72.6M
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 24, 2026
- Updated
- Feb 24, 2026
- SHA
- 49c41b06
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. -->
irish-whisper-combined-aug
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6851
- Wer: 30.7302
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 20000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4196 | 7.0672 | 2000 | 0.7531 | 46.2383 |
| 0.1137 | 14.1344 | 4000 | 0.7528 | 38.8904 |
| 0.0563 | 21.2016 | 6000 | 0.7506 | 38.1335 |
| 0.0474 | 28.2688 | 8000 | 0.7406 | 33.9795 |
| 0.0451 | 35.3360 | 10000 | 0.7460 | 35.1242 |
| 0.0228 | 42.4032 | 12000 | 0.7321 | 33.2041 |
| 0.0265 | 49.4704 | 14000 | 0.7366 | 33.6287 |
| 0.0343 | 56.5376 | 16000 | 0.7105 | 31.3579 |
| 0.0164 | 63.6048 | 18000 | 0.6946 | 30.7763 |
| 0.0109 | 70.6720 | 20000 | 0.6851 | 30.7302 |
Framework versions
- Transformers 5.3.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Feb 24, 2026
- Updated
- Feb 24, 2026