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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Chirag Bhardwaj's picture
7

Chirag Bhardwaj

chirag18

AI & ML interests

None yet

Recent Activity

new activity 6 days ago
deepakkaura/medasr-server:Lower KENLM_ALPHA to 0.05 — last try before disabling LM
new activity 6 days ago
deepakkaura/medasr-server:Re-download KenLM if size mismatches remote (cache invalidation)
updated a model 6 days ago
chirag18/radiology-stt-assets
View all activity

Organizations

None yet

New activity in deepakkaura/medasr-server 6 days ago

Lower KENLM_ALPHA to 0.05 — last try before disabling LM

#7 opened 6 days ago by
chirag18

Re-download KenLM if size mismatches remote (cache invalidation)

#6 opened 6 days ago by
chirag18
New activity in deepakkaura/medasr-server 7 days ago

Lower default KENLM_ALPHA 0.5→0.2, BETA 1.5→1.0

#5 opened 7 days ago by
chirag18

Use Python 3.10 (pypi-kenlm incompatible with 3.11)

#4 opened 7 days ago by
chirag18

Add C++ build deps so pypi-kenlm can compile in slim image

#3 opened 7 days ago by
chirag18

Download KenLM at server startup, not Docker build

#2 opened 7 days ago by
chirag18

Enable KenLM domain-LM shallow fusion at decode time

#1 opened 7 days ago by
chirag18
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs