magicunicorn/kokoro-npu-quantized
By magicunicorn · ↓ 0 · ♥ 3 · Updated 2025-07-10
What's in this repo
This page lists the files in magicunicorn/kokoro-npu-quantized, including kokoro-npu-fp16.onnx, kokoro-npu-quantized-int8.onnx.
- 2 ONNX models (.onnx files)
- 6 files, including 2 .md, 2 .onnx, 1 .bin
- Repository size ~7.5 KB
- Last updated 2025-07-10
ONNX files
| File | Size | Download |
|---|---|---|
| kokoro-npu-fp16.onnx | 134 B | Download |
| kokoro-npu-quantized-int8.onnx | 134 B | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
🎵 Kokoro NPU Quantized TTS Models
🎵 NPU-Optimized Text-to-Speech Models
NPU-optimized text-to-speech models for AMD Ryzen AI hardware.
Models Included
- kokoro-npu-quantized-int8.onnx (121.9 MB) - INT8 quantized for NPU
- kokoro-npu-fp16.onnx (169.8 MB) - FP16 for quality
- voices-v1.0.bin (26.9 MB) - Voice embeddings
Hardware Requirements
- NPU: NPU Phoenix
- Memory: 1GB+ available
- Framework: Unicorn Execution Engine
Quick Start
from unicorn_execution_engine import UnicornTTS
# Initialize NPU-accelerated TTS
tts = UnicornTTS(model="kokoro-npu-quantized")
# Generate speech with NPU acceleration
audio = tts.synthesize("Hello, this is NPU-accelerated speech!")
🎵 NPU-Accelerated Text-to-Speech
⚡ Powered by Unicorn Execution Engine
Model info
text-to-speech
onnx
onnx
tts
kokoro
npu
amd-ryzen-ai
quantized
text-to-speech
en
license:apache-2.0
region:us
↓ 0
♥ 3
Created: 2025-07-07
Updated: 2025-07-10
View on Hugging FaceFiles (6)
.gitattributes
README.md
TURBO_MODE_PERFORMANCE_UPDATE.md
kokoro-npu-fp16.onnx
134 B
ONNX
kokoro-npu-quantized-int8.onnx
134 B
ONNX
voices-v1.0.bin