Downloads · 30 days
3
2% of all-time downloads
wav2vec2-large-mms-1b-km-kag
bqkhanh/wav2vec2-large-mms-1b-km-kag
wav2vec2-large-mms-1b-km-kag is a machine learning model from bqkhanh. 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 cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
170
Public
Parameters
965M
151 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
At a glance
- License
- cc-by-nc-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jan 9, 2026
- Updated
- Jan 10, 2026
- SHA
- 970701ef
Base models
Datasets
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. -->
wav2vec2-large-mms-1b-km-kag
This model is a fine-tuned version of facebook/mms-1b-all on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.7023
- Wer: 0.9719
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.6022 | 0.4773 | 50 | 7.6316 | 1.0 |
| 4.2957 | 0.9547 | 100 | 1.5845 | 1.0002 |
| 0.4638 | 1.4320 | 150 | 0.7462 | 0.9896 |
| 0.3947 | 1.9093 | 200 | 0.7247 | 0.9819 |
| 0.3653 | 2.3866 | 250 | 0.7122 | 0.9763 |
| 0.375 | 2.8640 | 300 | 0.7079 | 0.9731 |
| 0.3425 | 3.3413 | 350 | 0.7112 | 0.9707 |
| 0.3319 | 3.8186 | 400 | 0.7080 | 0.9678 |
| 0.3336 | 4.2959 | 450 | 0.7023 | 0.9707 |
| 0.3355 | 4.7733 | 500 | 0.7023 | 0.9719 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu126
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Jan 9, 2026
- Updated
- Jan 10, 2026