Speech recognition models running on the Ryzen AI NPU with Windows ML.
🔄 In a Training Loop
Von
Harsha001
AI & ML interests
ROCmFPX GGUF quants for AMD GPUs and Strix Halo. Every file is scored by KLD against BF16. Speech models ported to the AMD XDNA2 NPU.
Recent Activity
updated a model about 16 hours ago
Harsha001/Raon-1-nano-ROCmFPX published a model about 16 hours ago
Harsha001/Raon-1-nano-ROCmFPX updated a model about 18 hours ago
Harsha001/Nex-N2.6-StrixHalo-GGUFOrganizations
None yet
models 38
Harsha001/Raon-1-nano-ROCmFPX
Text Generation • 3B • Updated • 22
Harsha001/Nex-N2.6-StrixHalo-GGUF
Image-Text-to-Text • 321B • Updated • 29
Harsha001/Arete-27B-Uncensored-ROCmFPX
Text Generation • 27B • Updated • 92
Harsha001/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-ROCmFPX
Image-Text-to-Text • 9B • Updated • 486
Harsha001/GLM-5.3-Flash-Uncensored-StrixHalo-GGUF
Text Generation • 321B • Updated • 87
Harsha001/Ripple-65B-abliterated-ROCmFPX
Text Generation • 65B • Updated • 332 • 2
Harsha001/Alpie-Seed-9B-ROCmFPX
Image-Text-to-Text • 9B • Updated • 134 • 1
Harsha001/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-StrixHalo-GGUF
Text Generation • 658B • Updated • 5.47k • 4
Harsha001/Pika-H3-Flex-ROCmFPX
Image-to-Video • 33B • Updated • 7.57k • 2
Harsha001/Drama-3-ROCmFPX-GGUF
Text-to-Speech • 36B • Updated • 1.16k • 1
datasets 0
None public yet