Downloads · 30 days
8
3% of all-time downloads
ERI-VAD
FanavaranPars/ERI-VAD
ERI-VAD is a machine learning model from FanavaranPars. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
The Speech Activity Recognition (VAD) module is used to manage audio files input to the Automatic Speech Recognition (ASR) system in various systems. With the ability to detect the presence of speech at the frame leve…
All-time downloads
257
Public
Parameters
199K
8.3 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors799 KB · 99%
At a glance
- Model type
- pyannote
- Access
- Public
- Created
- Sep 25, 2024
- Updated
- Dec 5, 2024
- SHA
- 8e7a31c7
Model card
From the Hugging Face model README
Design and development of audio activity detection services
The Speech Activity Recognition (VAD) module is used to manage audio files input to the Automatic Speech Recognition (ASR) system in various systems. With the ability to detect the presence of speech at the frame level, this module prevents ASR from wasting processing power on parts of the file that do not have speech content. In this chapter, the problem of speech activity recognition is explained first, and then the latest efficient models for speech activity recognition are introduced. Finally, the suitable models are trained with the VADS-V01 database and then their detailed evaluation is done.
- Type
- pyannote
- Created
- Sep 25, 2024
- Updated
- Dec 5, 2024