Downloads · 30 days
14
1% of all-time downloads
whisper-small-cv-ar
arbml/whisper-small-cv-ar
whisper-small-cv-ar is a automatic speech recognition model from arbml. 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
1.1K
Public
Repo size
2.9 GB
Likes
5
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 12, 2022
- Updated
- Aug 31, 2024
- SHA
- 655daa5b
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 - Zaid Alyafeai
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: 0.3509
- Wer: 22.3838
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: 8
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|
| 0.2944 | 0.2 | 1000 | 0.4355 | 30.6471 |
| 0.2671 | 0.4 | 2000 | 0.3786 | 25.8539 |
| 0.172 | 1.08 | 3000 | 0.3520 | 23.4573 |
| 0.1043 | 1.28 | 4000 | 0.3542 | 23.3278 |
| 0.0991 | 1.48 | 5000 | 0.3509 | 22.3838 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ar
- Created
- Dec 12, 2022
- Updated
- Aug 31, 2024