Hugging Face's logo 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

Muno459
/
fastconformer-quran-coreml-streaming

Automatic Speech Recognition
Core ML
Arabic
audio
arabic
quran
ios
on-device
ane
fastconformer
streaming
cache-aware
Model card Files Files and versions
xet
Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • fastconformer-quran-streaming.mlpackage
    Replace with ANE-VALIDATED streaming fp16 (29e, post-xscale +/-65504 saturate clamp; 11/11 ayat decode on ANE, 99.2%% residency, 5-8ms/chunk). Supersedes the distorting pre-clamp-2400 build. 2 months ago
  • pronunciation-head.mlpackage
    Replace pronunciation head with STREAMING-matched head (trained on 29e streaming-encoder features, [70,13] ctx) 2 months ago
  • .gitattributes
    1.52 kB
    Initial release 3 months ago
  • LICENSE
    4.65 kB
    Relicense under Quran-Lab No-Profit License v1.0 (NPL-1.0) about 2 months ago
  • README.md
    8.67 kB
    Relicense under Quran-Lab No-Profit License v1.0 (NPL-1.0) about 2 months ago
  • tokenizer.model
    255 kB
    xet
    Initial release 3 months ago
  • tokens.txt
    12.8 kB
    Initial release 3 months ago