Downloads · 30 days
3
9% of all-time downloads
whisper-medium-ar
gerryc/whisper-medium-ar
whisper-medium-ar is a automatic speech recognition model from gerryc. Use it when you need speech turned into text. It is set up for transformers.
Model was trained on CommonVoice Train. Tensorboard eval is on 256 samples of CommonVoice Dev.
All-time downloads
35
Public
Repo size
58.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- Dec 13, 2022
- Updated
- Dec 13, 2022
- SHA
- 5732b339
Model card
From the Hugging Face model README
Whisper Medium Ar - gerryc
Model was trained on CommonVoice Train. Tensorboard eval is on 256 samples of CommonVoice Dev.
Not normalized or lowercased. Evaluated and saved every 2500 steps. This model was overtrained and is overfitted. About 2000 to 4000 steps is around the best spot to stop training.
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- Languages
- ar
- Created
- Dec 13, 2022
- Updated
- Dec 13, 2022