Fun-ASR-Nano-2512-gguf is an open-source automatic speech recognition model distributed in GGUF format for local inference. It is designed for efficient offline speech-to-text transcription and supports quantized variants.
Fun ASR Nano 2512 is a Voice, TTS & speech product. It focuses on providing efficient offline speech-to-text transcription for developers and researchers. It is built as an open-source project for speech AI developers and researchers. Fun ASR Nano 2512 is open source under the MIT license. It runs on the command line, and it can be self-hosted.
Memoravox builds and maintains Fun ASR Nano 2512, and the product first shipped in 2026. Development happens publicly on GitHub with 176 stars and 458 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Fun ASR Nano 2512 occupies a relatively distinct niche. Key capabilities include Offline ASR, speech-to-text, and quantized models.
Latest indexed changes and source events
memoravox/Fun-ASR-Nano-2512-gguf discovered by the PulseGate indexer
Other apps tracked under the same category.
