SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR
Paper • 2605.20712 • Published • 3
Arghya Bhattacharya
orgh0
AI & ML interests
Natural Language Processing
Recent Activity
authored a paper about 7 hours ago
SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR reacted to kavyamanohar's post with 🚀 3 days 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 upvoted an article 8 days ago
Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic LanguagesOrganizations
authored a
paper about 7 hours ago
reacted to kavyamanohar's post with 🚀 3 days ago
Post
4499
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
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
upvoted an article 8 days ago
Article
Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages
adalat-ai
• • 11 updated a
dataset over 1 year ago
published a
dataset over 1 year ago