Downloads · 30 days
9
33% of all-time downloads
mdd-arabic-e9-xlsr300m-full-augmentation-beam
omarZACK/mdd-arabic-e9-xlsr300m-full-augmentation-beam
mdd-arabic-e9-xlsr300m-full-augmentation-beam is a automatic speech recognition model from omarZACK. 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
27
Public
Parameters
315M
1.3 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
- wav2vec2
- Access
- Public
- Created
- Aug 24, 2026
- Updated
- Aug 24, 2026
- SHA
- 2e8b3a2d
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. -->
mdd-arabic-e9-xlsr300m-full-augmentation-beam
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1003
- Per: 0.3347
- Accuracy: 0.6853
- Precision: 0.2844
- Recall: 0.2861
- F1 Macro: 0.2726
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- 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: 544
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Per | Accuracy | Precision | Recall | F1 Macro |
|---|---|---|---|---|---|---|---|---|
| 3.4742 | 1.0 | 364 | 3.6163 | 0.9869 | 0.0331 | 0.2638 | 0.2552 | 0.0270 |
| 2.4111 | 2.0 | 728 | 2.1305 | 0.6359 | 0.3941 | 0.2798 | 0.3443 | 0.1997 |
| 0.8583 | 3.0 | 1092 | 1.4276 | 0.3216 | 0.7045 | 0.3089 | 0.3269 | 0.3053 |
| 0.5947 | 4.0 | 1456 | 1.5337 | 0.3241 | 0.6985 | 0.3030 | 0.3177 | 0.2976 |
| 0.4253 | 5.0 | 1820 | 1.6968 | 0.3206 | 0.6985 | 0.2967 | 0.2949 | 0.2836 |
| 0.4401 | 6.0 | 2184 | 1.7728 | 0.3253 | 0.6932 | 0.2887 | 0.2913 | 0.2778 |
| 0.3332 | 7.0 | 2548 | 1.7882 | 0.3256 | 0.6930 | 0.2911 | 0.2971 | 0.2821 |
| 0.3131 | 8.0 | 2912 | 1.8732 | 0.3277 | 0.6912 | 0.2847 | 0.2872 | 0.2738 |
| 0.3040 | 9.0 | 3276 | 1.8606 | 0.3272 | 0.6911 | 0.2859 | 0.2887 | 0.2752 |
| 0.3322 | 10.0 | 3640 | 1.9809 | 0.3303 | 0.6896 | 0.2863 | 0.2872 | 0.2741 |
| 0.2755 | 11.0 | 4004 | 1.9927 | 0.3334 | 0.6863 | 0.2851 | 0.2874 | 0.2736 |
| 0.2421 | 12.0 | 4368 | 2.0042 | 0.3289 | 0.6889 | 0.2846 | 0.2856 | 0.2726 |
| 0.2092 | 13.0 | 4732 | 2.0267 | 0.3312 | 0.6888 | 0.2870 | 0.2907 | 0.2764 |
| 0.2196 | 14.0 | 5096 | 2.0920 | 0.3342 | 0.6858 | 0.2879 | 0.2889 | 0.2757 |
| 0.2018 | 15.0 | 5460 | 2.1003 | 0.3347 | 0.6853 | 0.2844 | 0.2861 | 0.2726 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.13.0+cu130
- Datasets 5.0.1
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Aug 24, 2026
- Updated
- Aug 24, 2026