Downloads · 30 days
54
0% of all-time downloads
hubert-large-arabic-egyptian
omarxadel/hubert-large-arabic-egyptian
hubert-large-arabic-egyptian is a automatic speech recognition model from omarxadel. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
This model is a fine-tuned version of Arabic Hubert-Large. We finetuned this model on the MGB-3 and Egyptian Arabic Conversational Speech Corpus datasets, acheiving a state of the art for Egyptian Arabic with WER of 2…
All-time downloads
14.9K
Public
Parameters
315M
2.5 GB on disk
Likes
22
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- hubert
- Access
- Public
- Created
- Jul 12, 2022
- Updated
- Mar 19, 2023
- SHA
- 80b042cd
Model card
From the Hugging Face model README
Arabic Hubert-Large - with CTC fine-tuned on MGB-3 and Egyptian Arabic Conversational Speech Corpus (No LM)
This model is a fine-tuned version of Arabic Hubert-Large. We finetuned this model on the MGB-3 and Egyptian Arabic Conversational Speech Corpus datasets, acheiving a state of the art for Egyptian Arabic with WER of 25.9%.
The original model was pre-trained on 2,000 hours of 16kHz sampled Arabic speech audio. When using the model make sure that your speech input is also sampled at 16Khz, see the original paper for more details on the model.
The performance of the model on the datasets is the following:
| Valid WER | Test WER |
|---|---|
| 23.55 | 25.59 |
Acknowledgement
Model fine-tuning and data processing for this work were performed as a part of a Graduation Project from Faculty of Engineering, Alexandria University, CCE Program.
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- hubert
- License
- cc-by-nc-4.0
- Languages
- ar
- Created
- Jul 12, 2022
- Updated
- Mar 19, 2023