Downloads · 30 days
0
whisper-at-mirror
nodja/whisper-at-mirror
whisper-at-mirror is a machine learning model from nodja. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-2-clause.
This is a mirror of the whisper-at pretrained models before they get lost in time. https://github.com/YuanGongND/whisper-at
Access
Public
Updated Mar 30, 2026
Repo size
896 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth896 MB · 100%
At a glance
- License
- bsd-2-clause
- Access
- Public
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026
- SHA
- 2a567da4
Model card
From the Hugging Face model README
This is a mirror of the whisper-at pretrained models before they get lost in time. https://github.com/YuanGongND/whisper-at
Whisper-AT is a joint audio tagging and speech recognition model. It inherits strong speech recognition ability from OpenAI Whisper, and its ASR performance is exactly the same as the original Whisper. The API interface and usage are also identical to the original OpenAI Whisper, so users can seamlessly switch from the original Whisper to Whisper-AT.
The advantage of Whisper-AT is that with minimal (less than 1%**) additional computational cost, Whisper-AT outputs general audio event labels (527-class AudioSet labels) in desired temporal resolution in addition to the ASR transcripts. This makes audio tagging much easier and faster than using a standalone audio tagging model.
Internally, Whisper-AT freezes all original Whisper parameters, and trains a Time- and Layer-wise Transformer (TL-TR) on top of the Whisper encoder representations for the audio tagging task.
- License
- bsd-2-clause
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026