viai957/indic-duplex-speech-artifacts download history

viai957/indic-duplex-speech-artifacts is an automatic speech recognition dataset on the Hugging Face Hub. In the last 30 days it was downloaded 173 times (30 in the last 7 days), and 173 times in total. It ranks #99,790 among datasets by monthly downloads.

Indic Duplex Speech Artifacts These are research artifacts from OmniVoxtral, a full-duplex speech language model for Indian languages. The repo holds: an Indic SentencePiece tokenizer; measurements of the Mimi neural codec on Indic speech; tokenizer fertility measurements; the uttera

Open viai957/indic-duplex-speech-artifacts on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.