Downloads · 30 days
6
3% of all-time downloads
TLT_spec_augment_whisper_small
Kwimp/TLT_spec_augment_whisper_small
TLT_spec_augment_whisper_small is a automatic speech recognition model from Kwimp. 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
203
Public
Parameters
242M
7.7 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
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- 92ef0992
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 small finetuned Specaug whole data
This model is a fine-tuned version of openai/whisper-small on the LTL2021 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4077
- Wer: 19.2088
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use 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: 2048
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.9313 | 1.7857 | 500 | 2.9922 | 18.7216 |
| 3.1440 | 3.5714 | 1000 | 1.8992 | 17.7254 |
| 1.7729 | 5.3571 | 1500 | 1.0467 | 18.1536 |
| 0.8745 | 7.1429 | 2000 | 0.4785 | 19.8532 |
| 0.7905 | 8.9286 | 2500 | 0.4280 | 20.8341 |
| 0.7137 | 10.7143 | 3000 | 0.4151 | 19.1520 |
| 0.6792 | 12.5 | 3500 | 0.4095 | 19.1804 |
| 0.6911 | 14.2857 | 4000 | 0.4077 | 19.2088 |
Framework versions
- Transformers 5.8.1
- Pytorch 2.5.1+cu121
- Datasets 4.8.5
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026