Downloads · 30 days
16
3% of all-time downloads
tiny-audio-next-thurs
mazesmazes/tiny-audio-next-thurs
tiny-audio-next-thurs is a feature extraction model from mazesmazes. Use it when you need embeddings to search or compare text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
560
Public
Parameters
602M
55.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- asr_model
- Access
- Public
- Created
- May 21, 2026
- Updated
- May 23, 2026
- SHA
- 14efb19f
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. -->
tiny-audio-next-thurs
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3428
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: 0.001
- train_batch_size: 100
- eval_batch_size: 100
- seed: 43
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2913 | 0.0450 | 2000 | 0.4665 |
| 0.2560 | 0.0900 | 4000 | 0.4262 |
| 0.2500 | 0.1350 | 6000 | 0.4156 |
| 0.2387 | 0.1800 | 8000 | 0.4142 |
| 0.2258 | 0.2250 | 10000 | 0.3964 |
| 0.2220 | 0.2700 | 12000 | 0.3896 |
| 0.2183 | 0.3150 | 14000 | 0.3913 |
| 0.2112 | 0.3600 | 16000 | 0.3841 |
| 0.2086 | 0.4050 | 18000 | 0.3763 |
| 0.2042 | 0.4501 | 20000 | 0.3732 |
| 0.1944 | 0.4951 | 22000 | 0.3659 |
| 0.1893 | 0.5401 | 24000 | 0.3631 |
| 0.1942 | 0.5851 | 26000 | 0.3589 |
| 0.1861 | 0.6301 | 28000 | 0.3567 |
| 0.1894 | 0.6751 | 30000 | 0.3515 |
| 0.1807 | 0.7201 | 32000 | 0.3497 |
| 0.1794 | 0.7651 | 34000 | 0.3456 |
| 0.1745 | 0.8101 | 36000 | 0.3453 |
| 0.1704 | 0.8551 | 38000 | 0.3459 |
| 0.1754 | 0.9001 | 40000 | 0.3446 |
| 0.1735 | 0.9451 | 42000 | 0.3440 |
| 0.1737 | 0.9901 | 44000 | 0.3415 |
| 0.1755 | 1.0 | 44439 | 0.3428 |
Framework versions
- Transformers 5.7.0
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2
- Task
- Feature Extraction
- Library
- transformers
- Type
- asr_model
- Created
- May 21, 2026
- Updated
- May 23, 2026