Introducing Moonshine, the new state of the art for speech to text
💻 Open sourced "Moonshine" speech to text model outperforms OpenAI's Whisper, offering 1.7x speed boost and flexibility in processing audio lengths, with a 5x speed advantage on ten second clips. Moonshine requires less RAM, targeting transcription in 8MB or less, ideal for devices like Raspberry Pi. The model powers the Torre translator for near-instant translations, enhancing conversation flow and operates locally for privacy.
Share
