Downloads · 30 days
5
0% of all-time downloads
wav2vec2-mdd-arab-grad-project
waelhasan/wav2vec2-mdd-arab-grad-project
wav2vec2-mdd-arab-grad-project is a automatic speech recognition model from waelhasan. 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
3.4K
Public
Parameters
94.4M
5.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- 5f455eae
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. -->
wav2vec2-mdd-arab-grad-project
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 232.5266
- Per: 0.0944
- F1: 0.9222
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Per | F1 |
|---|---|---|---|---|---|
| 10644.2969 | 1.0 | 104 | 1769.8489 | 1.0 | 0.0 |
| 3574.9772 | 2.0 | 208 | 1750.3961 | 1.0 | 0.0 |
| 3545.2557 | 3.0 | 312 | 1695.6754 | 1.0 | 0.0 |
| 2887.0763 | 4.0 | 416 | 950.4882 | 0.5267 | 0.6152 |
| 1578.4336 | 5.0 | 520 | 499.5067 | 0.2055 | 0.8318 |
| 992.7874 | 6.0 | 624 | 359.3315 | 0.1425 | 0.8840 |
| 744.5349 | 7.0 | 728 | 302.4440 | 0.1241 | 0.9000 |
| 610.2494 | 8.0 | 832 | 276.7447 | 0.1087 | 0.9108 |
| 528.7354 | 9.0 | 936 | 261.9057 | 0.1062 | 0.9128 |
| 471.6001 | 10.0 | 1040 | 248.0333 | 0.1025 | 0.9159 |
| 436.0370 | 11.0 | 1144 | 245.9362 | 0.0987 | 0.9189 |
| 405.6233 | 12.0 | 1248 | 236.4591 | 0.0979 | 0.9194 |
| 388.4592 | 13.0 | 1352 | 237.1770 | 0.0960 | 0.9208 |
| 373.4797 | 14.0 | 1456 | 232.7693 | 0.0940 | 0.9224 |
| 362.8645 | 15.0 | 1560 | 232.5266 | 0.0944 | 0.9222 |
Framework versions
- Transformers 5.14.1
- 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 2, 2026
- Updated
- Aug 2, 2026