Downloads · 30 days
17
53% of all-time downloads
uaspeech-whisper-lg-3-Nov3
sqrk/uaspeech-whisper-lg-3-Nov3
uaspeech-whisper-lg-3-Nov3 is a machine learning model from sqrk. 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
32
Public
Parameters
1.5B
117 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 3, 2024
- Updated
- Nov 28, 2024
- SHA
- cb72613b
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. -->
uaspeech-whisper-lg-3-Nov3
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0571
- Wer: 8.1245
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.7741 | 0.0719 | 100 | 0.6537 | 58.1245 |
| 0.4975 | 0.1437 | 200 | 0.4079 | 39.8141 |
| 0.3739 | 0.2156 | 300 | 0.3398 | 33.3872 |
| 0.3037 | 0.2875 | 400 | 0.2941 | 30.2344 |
| 0.2783 | 0.3593 | 500 | 0.2456 | 26.1116 |
| 0.2568 | 0.4312 | 600 | 0.2270 | 25.1011 |
| 0.2012 | 0.5031 | 700 | 0.2372 | 25.9903 |
| 0.2139 | 0.5749 | 800 | 0.1828 | 21.3015 |
| 0.1649 | 0.6468 | 900 | 0.1750 | 19.7656 |
| 0.149 | 0.7186 | 1000 | 0.1640 | 19.4826 |
| 0.146 | 0.7905 | 1100 | 0.1444 | 17.5829 |
| 0.1424 | 0.8624 | 1200 | 0.1305 | 15.5214 |
| 0.116 | 0.9342 | 1300 | 0.1294 | 16.3703 |
| 0.121 | 1.0061 | 1400 | 0.1210 | 16.1277 |
| 0.0755 | 1.0783 | 1500 | 0.1022 | 13.7833 |
| 0.0754 | 1.1502 | 1600 | 0.0814 | 11.1156 |
| 0.0919 | 1.2221 | 1700 | 0.0849 | 11.6815 |
| 0.0801 | 1.2939 | 1800 | 0.0827 | 11.4794 |
| 0.0751 | 1.3658 | 1900 | 0.0757 | 10.3476 |
| 0.0727 | 1.4377 | 2000 | 0.0820 | 11.2773 |
| 0.0797 | 1.5095 | 2100 | 0.0582 | 8.5287 |
| 0.0712 | 1.5814 | 2200 | 0.0672 | 10.2264 |
| 0.0655 | 1.6533 | 2300 | 0.0736 | 10.2668 |
| 0.0635 | 1.7251 | 2400 | 0.0641 | 9.4988 |
| 0.0646 | 1.7970 | 2500 | 0.0552 | 8.8521 |
| 0.0618 | 1.8688 | 2600 | 0.0596 | 8.3670 |
| 0.063 | 1.9407 | 2700 | 0.0517 | 7.7607 |
| 0.0628 | 2.0126 | 2800 | 0.0448 | 6.2247 |
| 0.029 | 2.0844 | 2900 | 0.0571 | 8.1245 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.1
- Datasets 3.0.0
- Tokenizers 0.19.1
- Type
- whisper
- License
- apache-2.0
- Created
- Nov 3, 2024
- Updated
- Nov 28, 2024