vconnx-triaan-vc

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.

Model card

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

Architecture

Three ONNX components chained in sequence:

  1. CPC encoder — 5-layer strided Conv1d (160× downsample) + LSTM; encodes speech to 256-dim content features at 100 Hz. Derived from facebookresearch/CPC_audio.
  2. TriAAN-VC decoder — SpeakerEncoder + ContentEncoder + BiGRU fusion + TriAAN decoder + PostNet; maps CPC features + log-F0 → 80-band mel spectrogram.
  3. ParallelWaveGAN vocoder — WaveNet-style neural vocoder (MIT, kan-bayashi); mel → 16 kHz waveform.

Files

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

Parity (PyTorch vs ONNX Runtime, random input, T=50 frames)

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).

Usage

from vconnx import VoiceCloner

vc = VoiceCloner(engine="triaan")
output_wav = vc.clone_voice(source_wav, target_wav)

Install:

pip install "vconnx[triaan]"

Provenance

Weights converted from the GitHub release v1.0 artifacts:

  • cpc.pt — CPC encoder checkpoint (facebookresearch/CPC_audio)
  • model-cpc-split.pth — TriAAN-VC decoder checkpoint
  • vocoder.pkl — ParallelWaveGAN vocoder checkpoint (originally from VQMIVC)

See PROVENANCE.md for full license text.

Downloads last month
12
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including TigreGotico/voiceclonnx-triaan-vc

Paper for TigreGotico/voiceclonnx-triaan-vc