Downloads · 30 days
11
2% of all-time downloads
mms-1b-ckt-chuklang-only
tadgeis/mms-1b-ckt-chuklang-only
mms-1b-ckt-chuklang-only is a automatic speech recognition model from tadgeis. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
592
Public
Parameters
965M
135 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.7 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- May 21, 2026
- Updated
- Jun 12, 2026
- SHA
- 45b9f119
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. -->
mms-1b-ckt-chuklang-only
This model is a fine-tuned version of facebook/mms-1b-all.
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: 16
- eval_batch_size: 8
- seed: 42
- 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: 25
- num_epochs: 36
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 6.2634 | 1.1905 | 50 | 1.1763 | 0.9333 | 0.2775 |
| 1.2315 | 2.3810 | 100 | 0.8655 | 0.8603 | 0.2226 |
| 1.0631 | 3.5714 | 150 | 0.8182 | 0.8175 | 0.2164 |
| 0.9782 | 4.7619 | 200 | 0.7653 | 0.7873 | 0.1946 |
| 0.9386 | 5.9524 | 250 | 0.7318 | 0.8095 | 0.1954 |
| 0.8568 | 7.1429 | 300 | 0.7501 | 0.7603 | 0.1900 |
| 0.8183 | 8.3333 | 350 | 0.7080 | 0.7571 | 0.1868 |
| 0.7862 | 9.5238 | 400 | 0.6988 | 0.7540 | 0.1804 |
| 0.7581 | 10.7143 | 450 | 0.7104 | 0.7571 | 0.1780 |
| 0.7122 | 11.9048 | 500 | 0.6984 | 0.7921 | 0.1858 |
| 0.6844 | 13.0952 | 550 | 0.6938 | 0.7270 | 0.1754 |
| 0.6783 | 14.2857 | 600 | 0.6841 | 0.7206 | 0.1727 |
| 0.6277 | 15.4762 | 650 | 0.6793 | 0.7111 | 0.1648 |
| 0.5747 | 16.6667 | 700 | 0.6875 | 0.7206 | 0.1654 |
| 0.6067 | 17.8571 | 750 | 0.6637 | 0.7238 | 0.1703 |
| 0.5725 | 19.0476 | 800 | 0.6746 | 0.7063 | 0.1654 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Languages
- ckt
- Created
- May 21, 2026
- Updated
- Jun 12, 2026