Downloads · 30 days
2
9% of all-time downloads
mdd-arabic-e7-xlsr1b-synthetic-arabic-error-beam
omarZACK/mdd-arabic-e7-xlsr1b-synthetic-arabic-error-beam
mdd-arabic-e7-xlsr1b-synthetic-arabic-error-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
23
Public
Parameters
963M
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- b0f6e417
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-e7-xlsr1b-synthetic-arabic-error-beam
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0402
- Per: 0.2099
- Accuracy: 0.7695
- Precision: 0.2787
- Recall: 0.2662
- F1 Macro: 0.2722
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
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Accuracy | F1 Macro | Validation Loss | Per | Precision | Recall |
|---|---|---|---|---|---|---|---|---|
| 1.4014 | 1.0 | 364 | 0.7851 | 0.3017 | 0.8642 | 0.2007 | 0.3028 | 0.3051 |
| 0.4352 | 2.0 | 728 | 0.7881 | 0.2910 | 0.9049 | 0.1920 | 0.3008 | 0.2821 |
| 0.7641 | 3.0 | 1092 | 0.7880 | 0.2884 | 0.8956 | 0.1906 | 0.2982 | 0.2795 |
| 0.4100 | 4.0 | 1456 | 0.7808 | 0.2807 | 0.9331 | 0.1969 | 0.2891 | 0.2728 |
| 0.3218 | 5.0 | 1820 | 0.9669 | 0.1968 | 0.7806 | 0.2878 | 0.2679 | 0.2772 |
| 0.2548 | 6.0 | 2184 | 0.9792 | 0.2008 | 0.7788 | 0.2877 | 0.2733 | 0.2803 |
| 0.2276 | 7.0 | 2548 | 1.0268 | 0.2080 | 0.7736 | 0.2880 | 0.2747 | 0.2812 |
| 0.2394 | 8.0 | 2912 | 1.0473 | 0.2066 | 0.7742 | 0.2931 | 0.2705 | 0.2810 |
| 0.1941 | 9.0 | 3276 | 1.0316 | 0.2104 | 0.7702 | 0.2860 | 0.2746 | 0.2801 |
| 0.1891 | 10.0 | 3640 | 1.0598 | 0.2060 | 0.7733 | 0.2885 | 0.2743 | 0.2812 |
| 0.1609 | 11.0 | 4004 | 1.0253 | 0.2054 | 0.7719 | 0.2802 | 0.2642 | 0.2719 |
| 0.1681 | 12.0 | 4368 | 1.0685 | 0.2145 | 0.7660 | 0.2793 | 0.2667 | 0.2728 |
| 0.1683 | 13.0 | 4732 | 1.0702 | 0.2097 | 0.7699 | 0.2784 | 0.2669 | 0.2724 |
| 0.1742 | 14.0 | 5096 | 1.0402 | 0.2099 | 0.7695 | 0.2787 | 0.2662 | 0.2722 |
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 21, 2026
- Updated
- Aug 21, 2026