https://nexgpu.net/en/models/funasr/
FunASR Self-Hosting: SenseVoice & Fun-ASR-Nano VRAM Requirements and GPU Picks | NexGPU | NexGPU
SenseVoiceSmall f16 weights are 470MB; the whole VAD+ASR+punctuation+speaker pipeline stays under 2GB. Run it on an RTX 3090 24GB at $0.193/GPU-hour.
self hostingfunasrsensevoicenanovram
https://github.com/modelscope/FunClip
GitHub - modelscope/FunClip: FunASR-powered video transcription, subtitle generation, and...
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI. - modelscope/FunClip
video transcriptiongithubmodelscopefunclipfunasr
https://www.funasr.com/en/docs/kubernetes.html
Kubernetes deployment - FunASR
Kubernetes deployment
kubernetesdeploymentfunasr
https://www.funasr.com/docs/model-selection.html
选择第一个模型 - FunASR
funasr
https://www.funasr.com/docs/repositories.html
四仓职责与贡献入口 - FunASR
funasr