Hugging Face
Models
Datasets
Spaces
Buckets
new
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
hatimqman
/
quran-stt-endpoint
like
0
ONNX
Model card
Files
Files and versions
xet
Community
Deploy
Copy to bucket
new
main
quran-stt-endpoint
312 MB
Ctrl+K
Ctrl+K
1 contributor
History:
30 commits
hatimqman
DIAG: per-stage timing + traceback + lib versions
d50f8d9
verified
about 1 month ago
__pycache__
نقطة استدلال: معالج + نموذج Saboor ONNX
2 months ago
head
acoustic layer: head/pronunciation_head.pt
2 months ago
tajweed
fix: thread cap + cpu torch (tajweed/aligner.py)
about 1 month ago
.gitattributes
Safe
1.58 kB
acoustic layer: model_with_encoder.q8.ort
2 months ago
handler.py
Safe
21.5 kB
DIAG: per-stage timing + traceback + lib versions
about 1 month ago
model_int8.onnx
Safe
175 MB
xet
نقطة استدلال: معالج + نموذج Saboor ONNX
2 months ago
model_with_encoder.q8.ort
Safe
132 MB
xet
acoustic layer: model_with_encoder.q8.ort
2 months ago
requirements.txt
Safe
145 Bytes
fix: keep base torch (no +cpu reinstall) — thread cap is the real fix
about 1 month ago
tokenizer.model
Safe
255 kB
xet
acoustic layer: tokenizer.model
2 months ago
tokens.txt
Safe
12.9 kB
نقطة استدلال: معالج + نموذج Saboor ONNX
2 months ago
