Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
Paper • 2605.13087 • Published • 3
Kumarmanas Nethil
janaab
AI & ML interests
speech, dialog systems and low-resource ML
Recent Activity
new activity 40 minutes ago
skit-ai/emotion-tts:Reformat dataset for Dataset Viewer + add Dataset Card reacted to kavyamanohar's post with 🚀 about 2 hours ago
Releasing Vividh-ASR — an open benchmark and models for Hindi and Malayalam ASR.
Vividh-ASR is built from public data, stratified by complexity:
→ Clean recordings
→ Noisy and accented speech
→ Spontaneous, conversational audio
Alongside the benchmark, we release:
→ Open models for Hindi and Malayalam
→ A training recipe with two counterintuitive choices that moved the needle
→ What failed, not just what worked
The stratified evaluation methodology transfers directly to any low-resource language setup — beyond Hindi and Malayalam.
Built at @adalatai, where we build speech tech for Indian courts. This is our first open contribution back to the community. @janaab @Kush0610 @orgh0
Link: https://huggingface.co/blog/adalat-ai/vividh-benchmark liked a dataset 2 days ago
L-NLProc/VidhikDastaavejOrganizations
authored a
paper 7 days ago
submitted a
paper to Daily Papers 7 days ago
authored a
paper 8 days ago
authored a
paper over 1 year ago