Popular repositories Loading
-
delayed-streams-modeling
delayed-streams-modeling PublicKyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
-
Repositories
Showing 10 of 15 repositories
- moshi Public
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’s past year of commit activity - delayed-streams-modeling Public
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
kyutai-labs/delayed-streams-modeling’s past year of commit activity - moshi-finetune Public
kyutai-labs/moshi-finetune’s past year of commit activity - moshi-swift Public
kyutai-labs/moshi-swift’s past year of commit activity - hibiki Public
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.
kyutai-labs/hibiki’s past year of commit activity