Downloads · 30 days
0
whisper-deepstack-tn-intent
FatimahEmadEldin/whisper-deepstack-tn-intent
whisper-deepstack-tn-intent is a audio classification model from FatimahEmadEldin. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is a small classifier head (~0.8M params) trained on top of frozen Whisper-large-v3 encoder features for Tunisian Arabic intent recognition as part of the NADI 2026 Shared Task.
Access
Public
Updated Jun 18, 2026
Repo size
24.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt24.6 MB · 100%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- 73eaea25
Datasets
Model card
From the Hugging Face model README
Whisper-DeepStack Tunisian Arabic Intent Classifier
This model is a small classifier head (~0.8M params) trained on top of frozen Whisper-large-v3 encoder features for Tunisian Arabic intent recognition as part of the NADI 2026 Shared Task.
Architecture
- Encoder:
openai/whisper-large-v3(frozen) - DeepStack Layers: [10, 21, 31]
- Aggregation: sum
- Validation Accuracy: 0.1513
- Validation Weighted F1: 0.0882
Usage
import torch
from huggingface_hub import hf_hub_download
ckpt = torch.load(
hf_hub_download("FatimahEmadEldin/whisper-deepstack-tn-intent", "best_classifier.pt"),
map_location='cpu'
)
- Task
- Audio Classification
- License
- apache-2.0
- Languages
- ar
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026