voiceclonnx — pure-ONNX voice conversion
Collection
ONNX exports powering the vconnx voice-conversion library: one repo per engine, with parity reports and provenance. • 10 items • Updated
Any-to-any voice conversion using TriAAN-VC (Triple Adaptive Attention Normalization, ICASSP 2023), exported to ONNX for CPU-first inference via the vconnx engine adapter.
| Field | Value |
|---|---|
| Paper | TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion |
| Original code | winddori2002/TriAAN-VC |
| License | MIT (original code and weights) |
| Sample rate | 16 000 Hz |
| Mel channels | 80 |
| FFT / hop / win | 400 / 160 / 400 samples |
Three ONNX components chained in sequence:
| File | Size | Description |
|---|---|---|
cpc_encoder.onnx |
7.0 MB | CPC content encoder (FP32) |
cpc_encoder_q8.onnx |
1.8 MB | CPC encoder INT8 dynamic quantization |
triaan_vc.onnx |
266.3 MB | TriAAN-VC decoder (FP32) |
triaan_vc_q8.onnx |
76.3 MB | TriAAN-VC decoder INT8 dynamic quantization |
pwg_vocoder.onnx |
7.0 MB | ParallelWaveGAN vocoder (FP32) |
pwg_vocoder_q8.onnx |
2.0 MB | PWG vocoder INT8 dynamic quantization |
config.json |
— | vconnx component manifest |
PROVENANCE.md |
— | Upstream provenance + license text |
| Component | max_abs Δ | mean_abs Δ | Verdict |
|---|---|---|---|
| CPC encoder | 1.06e-05 | 1.46e-07 | PASS |
| TriAAN-VC | 3.76e-06 | 6.39e-07 | PASS |
| ParallelWaveGAN | 4.39e-05 | 1.19e-06 | PASS |
All components pass with max_abs < 5e-05 (well within perceptual threshold).
from vconnx import VoiceCloner
vc = VoiceCloner(engine="triaan")
output_wav = vc.clone_voice(source_wav, target_wav)
Install:
pip install "vconnx[triaan]"
Weights converted from the GitHub release v1.0 artifacts:
cpc.pt — CPC encoder checkpoint (facebookresearch/CPC_audio)model-cpc-split.pth — TriAAN-VC decoder checkpointvocoder.pkl — ParallelWaveGAN vocoder checkpoint (originally from VQMIVC)See PROVENANCE.md for full license text.