AI & ML interests

Physical AI, robotics, embodied AI, egocentric video, robot manipulation, humanoid training data, imitation learning, multimodal datasets, speech & voice data, multilingual ASR, 3D, consented & commercially licensed training data

Recent Activity

krisarelΒ  updated a dataset 12 days ago
psdn-ai/CROWS-multilingual
yashvyas7Β  updated a dataset 26 days ago
psdn-ai/CROWS-multilingual
krisarelΒ  updated a Space about 1 month ago
psdn-ai/README
View all activity

ksrupaakulaΒ 
posted an update 12 days ago
view post
Post
2,779
Evaluating ASR beyond short clips: our Numo Indic Speech releases provide longer-form transcribed audio across four languages:

Hindi: 46.6s average duration
Telugu: 33.3s
Tamil: 32.7s
Bengali: 46.5s

For comparison, Common Voice 26.0 averages roughly 4–6 seconds across these languages.

These longer recordings support research into segmentation, context retention, streaming, and endpointing behavior.

The four datasets are available under controlled access. Check them out: psdn-ai/numo-indic-speech
  • 1 reply
Β·
krisarelΒ 
updated a Space about 1 month ago
krisarelΒ 
published a Space about 1 month ago
RN0311Β 
posted an update 2 months ago
view post
Post
4,017
SONAR is now open-source! πŸ”Š

SONAR is an evaluation toolkit for multilingual ASR that goes beyond WER/CER. It combines semantic similarity, the Poseidon Score, and analysis across dialect, demographic, and metadata-based failure modes. 🌍

Our goal is to make it easier for everyone to understand why an ASR model fails, not just how often. πŸ” You can plug in your own models + audio, extend it to new languages and datasets, or contribute directly. πŸ› οΈ

MIT licensed. Would love feedback from the HF community! πŸ€—

πŸ”— GitHub: https://github.com/PSDN-AI/SONAR-OSS/
πŸ”— Blog: https://www.psdn.ai/blog/open-source-multilingual-asr-evaluation