shangeth/expresso-mimi-codes download history

shangeth/expresso-mimi-codes is a text to speech dataset on the Hugging Face Hub. In the last 30 days it was downloaded 56 times (22 in the last 7 days), and 469 times in total. It ranks #171,127 among datasets by monthly downloads.

Expresso — Mimi Codes (k = 32) Pre-extracted Kyutai Mimi tokens (all 32 codebooks) for both the read and conversational subsets of Expresso. Source audio + transcripts live in shangeth/expresso; this dataset publishes the discrete-token version for training Mimi-based speech models withou

Open shangeth/expresso-mimi-codes on Hugging Face

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