Downloads · 30 days
6
2% of all-time downloads
distill
Ahmed107/distill
distill is a automatic speech recognition model from Ahmed107. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
257
Public
Parameters
756M
3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Nov 8, 2023
- Updated
- Nov 8, 2023
- SHA
- d34b82a2
Base models
Datasets
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. -->
Hamsa distill alfa
This model is a fine-tuned version of distil-whisper/distil-large-v2 on the nadsoft/Jordan-Audio dataset. It achieves the following results on the evaluation set:
- Loss: 0.8474
- Wer Ortho: 56.1657
- Wer: 54.1123
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.7394 | 1.76 | 500 | 0.8474 | 56.1657 | 54.1123 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- mit
- Languages
- ar
- Created
- Nov 8, 2023
- Updated
- Nov 8, 2023