Downloads · 30 days
180
27% of all-time downloads
PhoWhisper-small
huuquyet/PhoWhisper-small
PhoWhisper-small is a automatic speech recognition model from huuquyet. Use it when you need speech turned into text. It is set up for transformers.js. The card lists the license as wtfpl.
https://hf.co/vinai/PhoWhisper-small with ONNX weights to be compatible with Transformers.js.
All-time downloads
656
Public
Repo size
12.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx2.7 GB · 73%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers.js
- License
- wtfpl
- Model type
- whisper
- Access
- Public
- Created
- Apr 9, 2024
- Updated
- Jun 13, 2024
- SHA
- 515c6b55
Spaces
Model card
From the Hugging Face model README
https://hf.co/vinai/PhoWhisper-small with ONNX weights to be compatible with Transformers.js.
Please check out this demo using the model:
PhoWhisper: Automatic Speech Recognition for Vietnamese
We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual Whisper on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software:
@inproceedings{PhoWhisper,
title = {{PhoWhisper: Automatic Speech Recognition for Vietnamese}},
author = {Thanh-Thien Le and Linh The Nguyen and Dat Quoc Nguyen},
booktitle = {Proceedings of the ICLR 2024 Tiny Papers track},
year = {2024}
}
For further information or requests, please go to PhoWhisper's homepage!
- Task
- Automatic Speech Recognition
- Library
- transformers.js
- Type
- whisper
- License
- wtfpl
- Languages
- vi
- Created
- Apr 9, 2024
- Updated
- Jun 13, 2024