Downloads · 30 days
12
24% of all-time downloads
hubert-large-timit-upsample-4-50
nh0znoisung/hubert-large-timit-upsample-4-50
hubert-large-timit-upsample-4-50 is a machine learning model from nh0znoisung. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
49
Public
Parameters
315M
18.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- hubert
- Access
- Public
- Created
- May 8, 2025
- Updated
- May 9, 2025
- SHA
- f783d836
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. -->
hubert-large-timit-upsample-4-50
This model is a fine-tuned version of facebook/hubert-large-ls960-ft on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1708
- Wer: 0.7941
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5553 | 2.4752 | 500 | 0.4724 | 0.9855 |
| 0.3331 | 4.9505 | 1000 | 0.2739 | 0.9504 |
| 0.2707 | 7.4257 | 1500 | 0.2362 | 0.9635 |
| 0.2411 | 9.9010 | 2000 | 0.2191 | 0.9122 |
| 0.2246 | 12.3762 | 2500 | 0.2068 | 0.8596 |
| 0.2088 | 14.8515 | 3000 | 0.1971 | 0.8365 |
| 0.1951 | 17.3267 | 3500 | 0.1918 | 0.8261 |
| 0.187 | 19.8020 | 4000 | 0.1864 | 0.8227 |
| 0.1769 | 22.2772 | 4500 | 0.1851 | 0.8210 |
| 0.1728 | 24.7525 | 5000 | 0.1811 | 0.8250 |
| 0.1682 | 27.2277 | 5500 | 0.1730 | 0.8135 |
| 0.1662 | 29.7030 | 6000 | 0.1708 | 0.7941 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.2.1
- Datasets 3.6.0
- Tokenizers 0.21.1
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- May 8, 2025
- Updated
- May 9, 2025