Downloads · 30 days
0
Whisper-large-Arabic-phoneme
nrshoudi/Whisper-large-Arabic-phoneme
Whisper-large-Arabic-phoneme is a machine learning model from nrshoudi. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Nov 25, 2023
Repo size
14.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.2 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Nov 25, 2023
- Updated
- Nov 25, 2023
- SHA
- 4a11bda6
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. -->
Whisper-large-Arabic-phoneme
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2133
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: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0577 | 1.0 | 546 | 0.2082 |
| 0.0362 | 2.0 | 1092 | 0.1947 |
| 0.0291 | 3.0 | 1638 | 0.1888 |
| 0.0159 | 4.0 | 2184 | 0.1927 |
| 0.0177 | 5.0 | 2730 | 0.1870 |
| 0.0164 | 6.0 | 3276 | 0.1914 |
| 0.0111 | 7.0 | 3822 | 0.2031 |
| 0.0048 | 8.0 | 4368 | 0.2088 |
| 0.0025 | 9.0 | 4914 | 0.2106 |
| 0.0014 | 10.0 | 5460 | 0.2133 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- License
- apache-2.0
- Created
- Nov 25, 2023
- Updated
- Nov 25, 2023