Downloads · 30 days
4
3% of all-time downloads
120min_whisper_small_FT_1e_5
khier12/120min_whisper_small_FT_1e_5
120min_whisper_small_FT_1e_5 is a automatic speech recognition model from khier12. 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
129
Public
Parameters
242M
19.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jan 19, 2026
- Updated
- Jan 20, 2026
- SHA
- afef3986
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. -->
120min_whisper_small_FT_1e_5
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1247
- Wer: 59.7692
- Cer: 21.5313
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 400
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|---|---|---|---|---|---|
| 0.5105 | 0.7634 | 100 | 24.4591 | 0.8714 | 65.0016 |
| 0.5478 | 1.5267 | 200 | 25.0686 | 0.8271 | 63.9583 |
| 0.3876 | 2.2901 | 300 | 24.8154 | 0.8435 | 63.0651 |
| 0.3008 | 3.0534 | 400 | 25.4704 | 0.8605 | 65.7683 |
| 0.2037 | 3.8168 | 500 | 26.1163 | 0.9008 | 63.9346 |
| 0.0794 | 4.5802 | 600 | 24.9943 | 0.9336 | 64.2586 |
| 0.0775 | 5.3435 | 700 | 23.7965 | 0.9494 | 62.8280 |
| 0.042 | 6.1069 | 800 | 23.1597 | 0.9661 | 61.2393 |
| 0.023 | 6.8702 | 900 | 22.0347 | 1.0048 | 60.1881 |
| 0.0172 | 7.6336 | 1000 | 21.7997 | 1.0287 | 60.0537 |
| 0.0107 | 8.3969 | 1100 | 22.5790 | 1.0427 | 60.2988 |
| 0.0067 | 9.1603 | 1200 | 21.2220 | 1.0573 | 59.6032 |
| 0.0065 | 9.9237 | 1300 | 21.2387 | 1.0705 | 59.5953 |
| 0.0065 | 10.6870 | 1400 | 1.0844 | 59.2475 | 21.1356 |
| 0.0042 | 11.4504 | 1500 | 1.1009 | 59.8957 | 21.4434 |
| 0.0022 | 12.2137 | 1600 | 1.1045 | 59.4135 | 21.4101 |
| 0.0024 | 12.9771 | 1700 | 1.1133 | 59.8245 | 21.4358 |
| 0.0018 | 13.7405 | 1800 | 1.1205 | 59.5953 | 21.5162 |
| 0.0014 | 14.5038 | 1900 | 1.1239 | 59.8561 | 21.6072 |
| 0.0014 | 15.2672 | 2000 | 1.1247 | 59.7692 | 21.5313 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 2.21.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jan 19, 2026
- Updated
- Jan 20, 2026