Popular repositories Loading

1. moshi 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.

   Python 8.8k 772

2. delayed-streams-modeling delayed-streams-modeling Public

   Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

   Python 2.2k 208

3. hibiki 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--- H…

   Rust 1.3k 94

4. unmute unmute Public

   Make text LLMs listen and speak

   Python 800 126

5. moshi-finetune moshi-finetune Public

   Python 279 29

6. moshivis moshivis Public

   Kyutai with an "eye"

   Python 216 27