Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Nmaghura
/
VoxaPlus
Like
0
Automatic Speech Recognition
PyTorch
7 datasets
Arabic
Moroccan Arabic
darija
moroccan-arabic
speech-recognition
fastconformer
tdt
pseudo-labeling
Eval Results (legacy)
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
VoxaPlus
251 MB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
Nmaghura
Update README.md
5f97b55
verified
about 12 hours ago
.gitattributes
Safe
1.52 kB
initial commit
2 days ago
README.md
11.4 kB
Update README.md
about 12 hours ago
fastconformer.py
Safe
5.78 kB
VoxaPlus v1: full MoulSot test WER 39.84, CER 15.14
2 days ago
parakeet_data.py
Safe
4.03 kB
VoxaPlus v1: full MoulSot test WER 39.84, CER 15.14
2 days ago
parakeet_model.py
Safe
6.26 kB
VoxaPlus v1: full MoulSot test WER 39.84, CER 15.14
2 days ago
tokenizer_bpe1024.json
Safe
51.5 kB
VoxaPlus v1: full MoulSot test WER 39.84, CER 15.14
2 days ago
voxaplus.pt
251 MB
xet
VoxaPlus phase 4: all moulsot.v0.3 pseudo-labels (541 h) + oddadmix Darija + MSA replay - MoulSot test WER 36.87 / CER 14.08 (phase 3: 38.30 / 14.55), MASC MSA WER 20.99 / CER 8.04 (phase 3: 31.66 / 10.86)
about 13 hours ago
