Downloads · 30 days
0
ASR_verbatim_v1
nelfproject/ASR_verbatim_v1
ASR_verbatim_v1 is a machine learning model from nelfproject. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains the first version of our Automatic Speech Recognition and Subtitle Generation model, trained on 2000 hours of Flemish broadcast subtitled speech data. It is converted to a simple ASR model, wh…
Access
Public
Updated Jul 10, 2024
Repo size
188 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth188 MB · 100%
At a glance
- Access
- Public
- Created
- Sep 25, 2023
- Updated
- Jul 10, 2024
- SHA
- 952a15bd
Model card
From the Hugging Face model README
Model
This repository contains the first version of our Automatic Speech Recognition and Subtitle Generation model, trained on 2000 hours of Flemish broadcast subtitled speech data. It is converted to a simple ASR model, which outputs only a verbatim transcription.
Version: September 2023
Usage
This repository only hosts the pre-trained model itself and the configuration files. To download this model, see the instructions here.
Usage of this model, as well as our other ASR models, is integrated in our Github codebase. Please refer to the Github for installation.
Webservice
This model can also be accessed through the webservice of the NeLF Project. After requesting access, you can upload audio or video files and they will be transcribed according to the desired settings.
Citation
If you use this model, please cite the research paper: (Will be added shortly).
Contact
Jakob Poncelet: jakob.poncelet@kuleuven.be
- Languages
- nl
- Created
- Sep 25, 2023
- Updated
- Jul 10, 2024