Search Results for "mimi"

x
Sort By:

Showing 1 open source project for "mimi"

View related business solutions
Sound/Audio Python Clear Filters & Widen Search
  • Atera all-in-one platform IT management software with AI agents Icon
    Atera all-in-one platform IT management software with AI agents

    Ideal for internal IT departments or managed service providers (MSPs)

    Atera’s AI agents don’t just assist, they act. From detection to resolution, they handle incidents and requests instantly, taking your IT management from automated to autonomous.
    Learn More
  • Total Network Visibility for Network Engineers and IT Managers Icon
    Total Network Visibility for Network Engineers and IT Managers

    Network monitoring and troubleshooting is hard. TotalView makes it easy.

    This means every device on your network, and every interface on every device is automatically analyzed for performance, errors, QoS, and configuration.
    Learn More
  • 1
    Moshi

    Moshi

    A speech-text foundation model for real time dialogue

    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. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps).
    Downloads: 5 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • Next

Related Categories