ModelWhisper / OpenAI Whisper
Whisper ASR
An open-source automatic speech recognition (ASR) model developed by OpenAI. It supports multilingual transcription and translation, offers high accuracy, and can be deployed locally. It is widely used in homelab and local AI applications.
Timeline (last 90 days)
Oct 12
The experimental environment is built around a single NVIDIA RTX 3090 (24 GB VRAM, 390 W power limit), on which two shared services run: a Whisper ASR transcription service and nomic-embed-text (Ollama).
Unverified50%