Downloads · 30 days
12
5% of all-time downloads
hubert-large-ll60k-gui
ctaguchi/hubert-large-ll60k-gui
hubert-large-ll60k-gui is a automatic speech recognition model from ctaguchi. 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
227
Public
Parameters
315M
56.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- hubert
- Access
- Public
- Created
- Feb 10, 2026
- Updated
- Feb 13, 2026
- SHA
- 9f717bd7
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-ll60k-gui
This model is a fine-tuned version of facebook/hubert-large-ll60k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6727
- Cer: 0.1933
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 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: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 12.4899 | 0.4329 | 100 | 2.9461 | 1.0 |
| 4.7183 | 0.8658 | 200 | 1.4448 | 0.4452 |
| 2.4493 | 1.2987 | 300 | 0.9741 | 0.2895 |
| 1.9175 | 1.7316 | 400 | 0.8473 | 0.2858 |
| 1.7261 | 2.1645 | 500 | 0.7686 | 0.2300 |
| 1.3808 | 2.5974 | 600 | 0.7090 | 0.2246 |
| 1.3589 | 3.0303 | 700 | 0.7337 | 0.2025 |
| 1.0326 | 3.4632 | 800 | 0.6990 | 0.2021 |
| 1.0262 | 3.8961 | 900 | 0.6383 | 0.2029 |
| 0.8421 | 4.3290 | 1000 | 0.7237 | 0.1869 |
| 0.8643 | 4.7619 | 1100 | 0.7168 | 0.1850 |
| 0.8911 | 5.1948 | 1200 | 0.6574 | 0.1889 |
| 0.9163 | 5.6277 | 1300 | 0.7811 | 0.1909 |
| 1.1833 | 6.0606 | 1400 | 0.7522 | 0.2140 |
| 1.0550 | 6.4935 | 1500 | 0.7212 | 0.1984 |
| 0.9478 | 6.9264 | 1600 | 0.6839 | 0.1954 |
| 0.8443 | 7.3593 | 1700 | 0.6707 | 0.2012 |
| 0.8298 | 7.7922 | 1800 | 0.6808 | 0.1937 |
| 0.8577 | 8.2251 | 1900 | 0.6879 | 0.1920 |
| 0.7843 | 8.6580 | 2000 | 0.6800 | 0.1924 |
| 0.8018 | 9.0909 | 2100 | 0.6794 | 0.1921 |
| 0.7750 | 9.5238 | 2200 | 0.6781 | 0.1935 |
| 0.7869 | 9.9567 | 2300 | 0.6727 | 0.1933 |
Framework versions
- Transformers 5.1.0
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- Feb 10, 2026
- Updated
- Feb 13, 2026