Found 3 bookmarks
Newest
kyutai-labs/moshi: Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
kyutai-labs/moshi: Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. - kyutai-labs/moshi
AIAI#AI#Audio#Chatbot#Open Source#S2TXT
·github.com·
kyutai-labs/moshi: Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.