Downloads · 30 days
42
8% of all-time downloads
wav2vec2-large-xls-r-300m-Arabic-MDD
nrshoudi/wav2vec2-large-xls-r-300m-Arabic-MDD
wav2vec2-large-xls-r-300m-Arabic-MDD is a automatic speech recognition model from nrshoudi. 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
516
Public
Repo size
79.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- May 18, 2023
- Updated
- Jun 11, 2023
- SHA
- c5afe81f
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-xls-r-300m-Arabic-MDD
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0204
- Per: 0.0096
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Per |
|---|---|---|---|---|
| 8.4892 | 1.0 | 51 | 3.3287 | 1.0 |
| 2.5606 | 1.99 | 102 | 2.0472 | 1.0 |
| 2.0523 | 2.99 | 153 | 2.0184 | 1.0 |
| 1.9865 | 4.0 | 205 | 1.9865 | 1.0 |
| 1.9854 | 5.0 | 256 | 1.9408 | 0.9934 |
| 1.9603 | 5.99 | 307 | 1.9124 | 0.9937 |
| 1.8169 | 6.99 | 358 | 1.6965 | 0.9871 |
| 1.5596 | 8.0 | 410 | 1.4850 | 0.9779 |
| 1.3494 | 9.0 | 461 | 1.1074 | 0.9782 |
| 0.9242 | 9.99 | 512 | 0.6071 | 0.7359 |
| 0.5172 | 10.99 | 563 | 0.2910 | 0.2875 |
| 0.3105 | 12.0 | 615 | 0.1489 | 0.1075 |
| 0.186 | 13.0 | 666 | 0.0938 | 0.0342 |
| 0.1437 | 13.99 | 717 | 0.0809 | 0.0255 |
| 0.1185 | 14.99 | 768 | 0.0665 | 0.0127 |
| 0.0952 | 16.0 | 820 | 0.0409 | 0.0103 |
| 0.0721 | 17.0 | 871 | 0.0291 | 0.0107 |
| 0.0575 | 17.99 | 922 | 0.0228 | 0.0089 |
| 0.0503 | 18.99 | 973 | 0.0216 | 0.0100 |
| 0.0439 | 19.9 | 1020 | 0.0204 | 0.0096 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 18, 2023
- Updated
- Jun 11, 2023