GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

voconly author hub

Nemotron 3.5 ASR Streaming 0.6B GGUF NVIDIA 推出的轻量级流式多语言语音识别模型,支持32种语言,专为实时转录场景优化。 模型简介 NVIDIA Nemotron 3.5 ASR Streaming 是专为实时流式处理设计的多语言语音识别模型: 参数量 :0.6B 600M 语言支持 :32种语言(含中英日韩及欧洲主要语言) 量化格式 :GGUF llama.cpp 兼容 特点 :流式处理、低延迟、轻量级、多语言 适用场景 :实时字幕、直播转写、语音助手、会议实时记录 支持语言 32种 | 语言 | 代码 | …

Models
6
Downloads
0
voconly/whisper-large-v3-turbo-gguf
0 downloads · automatic-speech-recognition
voconly/parakeet-tdt-0.6b-v3-gguf
0 downloads · automatic-speech-recognition
voconly/nemotron-3.5-asr-streaming-0.6b-gguf
0 downloads · automatic-speech-recognition
voconly/cohere-transcribe-03-2026-gguf
0 downloads · automatic-speech-recognition
voconly/Qwen3-ASR-1.7B-gguf
0 downloads · automatic-speech-recognition

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models