1 Repo
Techniques for processing asynchronous data streams where binary masks determine which entries in a batch are active.
Distinct from Batch Processing: Specific to using masks to protect internal state in asynchronous streams, rather than general bulk data operations
Explore 1 awesome GitHub repository matching data & databases · Execution Masking. Refine with filters or upvote what's useful.
Moshi is a real-time voice foundation model and speech-to-speech framework designed for bidirectional, low-latency conversations. It functions as a full-duplex voice interface that processes audio and text concurrently in a single stream, enabling natural human-machine dialogue without sequential processing delays. The system utilizes a neural audio codec to compress high-fidelity audio into low-bitrate tokens for efficient transmission. To manage complex responses and reasoning, it employs internal monologue modeling, which generates a hidden stream of thought tokens alongside audible speech
Manages asynchronous data batches using execution masks to protect the internal state of ignored entries.