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 2 hours ago
Harsha001/Ripple-65B-Preview-ROCmFPX published a model 1 day ago
Harsha001/Ripple-65B-Preview-ROCmFPX liked a model 2 days ago
moonshotai/Kimi-K3.1-ProOrganizations
None yet
models 32
Harsha001/Ripple-65B-Preview-ROCmFPX
Text Generation • 65B • Updated • 1
Harsha001/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-StrixHalo-GGUF
Text Generation • 658B • Updated • 2.57k • 4
Harsha001/Pika-H3-Flex-ROCmFPX
Image-to-Video • 33B • Updated • 62 • 2
Harsha001/Drama-3-ROCmFPX-GGUF
Text-to-Speech • 36B • Updated • 1.15k • 1
Harsha001/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-ROCmFPX
Automatic Speech Recognition • 0.8B • Updated • 204
Harsha001/Audio8-TTS-Realistic-0.6b-ROCmFPX
Text-to-Speech • 0.5B • Updated • 174
Harsha001/Qwen4-Flash-Next-ROCmFPX
Image-Text-to-Text • Updated
Harsha001/Qwen3.8-27B-Uncensored-ROCmFPX
Image-Text-to-Text • 27B • Updated • 815 • 1
Harsha001/Clover-35B-A3B-Preview-ROCmFPX
Text Generation • 35B • Updated • 389
Harsha001/Groot-19B-A3B-261023-ROCmFPX
Image-Text-to-Text • 19B • Updated • 336
datasets 0
None public yet