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 1 hour ago
Harsha001/Alpie-Seed-9B-ROCmFPX published a model about 1 hour ago
Harsha001/Alpie-Seed-9B-ROCmFPX updated a model about 8 hours ago
Harsha001/Ripple-65B-Preview-ROCmFPXOrganizations
None yet
models 33
Harsha001/Alpie-Seed-9B-ROCmFPX
Image-Text-to-Text • 9B • Updated
Harsha001/Ripple-65B-Preview-ROCmFPX
Text Generation • 4B • Updated • 70 • 1
Harsha001/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-StrixHalo-GGUF
Text Generation • 658B • Updated • 2.6k • 4
Harsha001/Pika-H3-Flex-ROCmFPX
Image-to-Video • 33B • Updated • 79 • 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 • 214
Harsha001/Audio8-TTS-Realistic-0.6b-ROCmFPX
Text-to-Speech • 0.5B • Updated • 213
Harsha001/Qwen4-Flash-Next-ROCmFPX
Image-Text-to-Text • Updated
Harsha001/Qwen3.8-27B-Uncensored-ROCmFPX
Image-Text-to-Text • 27B • Updated • 829 • 1
Harsha001/Clover-35B-A3B-Preview-ROCmFPX
Text Generation • 35B • Updated • 407
datasets 0
None public yet