Voiceclonnx 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.
Source du modèle
- Type
- Other
- Taille du fichier
- 1,81–266 MB
- Version
- vRevision 0ecc46e
- Mis à jour
- 25 oct. 2026
- Téléchargements
- 10
- Source
- Hugging Face
Description de la source
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:
- CPC encoder — 5-layer strided Conv1d (160× downsample) + LSTM; encodes speech to 256-dim content features at 100 Hz. Derived from facebookresearch/CPC_audio.
- TriAAN-VC decoder — SpeakerEncoder + ContentEncoder + BiGRU fusion + TriAAN decoder + PostNet; maps CPC features + log-F0 → 80-band mel spectrogram.
- 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 checkpointvocoder.pkl— ParallelWaveGAN vocoder checkpoint (originally from VQMIVC)
See PROVENANCE.md for full license text.
Sources
1 source
Sources
1 sourceVérifié 25 oct.
Download files
Artefacts du modèle
6 artefacts
Artefacts du modèle
6 artefactsExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: mit tags: - voice-conversion - any-to-any - onnx - vconnx language: - en pipeline_tag: audio-to-audio --- # 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](https://github.com/TigreGotico/vconnx) engine adapter. ## Model card | Field | Value | |---|---| | Paper | [TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion](https://arxiv.org/abs/2303.09057) | | Original code | [winddori2002/TriAAN-VC](https://github.com/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](https://github.com/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 ```python from vconnx import VoiceCloner vc = VoiceCloner(engine="triaan") output_wav = vc.clone_voice(source_wav, target_wav) ``` Install: ```bash...
Source context: 10 downloads · 0 likes · Pipeline audio-to-audio · Repo TigreGotico/voiceclonnx-triaan-vc
Source context: 9 downloads · 0 likes · Pipeline audio-to-audio · Repo TigreGotico/voiceclonnx-triaan-vc
