At a guess, based on model size, just about anything, even a Raspberry Pi 4 etc....

		detrites on May 22, 2023 \| parent \| context \| favorite \| on: Meta AI announces Massive Multilingual Speech code... At a guess, based on model size, just about anything, even a Raspberry Pi 4 etc. As comparison the GGML port of Whisper (OpenAI's equivalent), runs in the browser, via WASM: https://whisper.ggerganov.com/

If this is the case, what hardware is needed for real-time tts?