Downloads · 30 days
10
3% of all-time downloads
whisper-small-ar
hkhdair/whisper-small-ar
whisper-small-ar is a automatic speech recognition model from hkhdair. 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
374
Public
Repo size
5.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 7, 2022
- Updated
- Dec 10, 2022
- SHA
- fa593c94
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 small ar - fine-tune Alpha
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4592
- Wer: 59.8813
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2057 | 1.66 | 1000 | 0.3395 | 61.9160 |
| 0.0859 | 3.32 | 2000 | 0.3406 | 57.3707 |
| 0.0513 | 4.98 | 3000 | 0.3730 | 62.0467 |
| 0.0157 | 6.64 | 4000 | 0.4284 | 60.84 |
| 0.0072 | 8.31 | 5000 | 0.4592 | 59.8813 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ar
- Created
- Dec 7, 2022
- Updated
- Dec 10, 2022