Skip to content
ModelListedExternal
Browse files

Aiden v1

Single-speaker RVC v2 model trained on Jaiden (17yo male) for the Paion project.

Sourcehuggingface.co/jeffhm14/aiden-v1/tree/37f51b0401e80165c5cf8f76cffd74a879e4aad9
KindOtherVersionRevision 37f51b0Cgrade

Model source

Kind
Other
File size
53.6 MB
Version
vRevision 37f51b0
Updated
Oct 31, 2026
Downloads
9
Source
Hugging Face

Source description

AIDEN — Acoustic Intonation Decoder + Expressive Neural

Single-speaker RVC v2 model trained on Jaiden (17yo male) for the Paion project.

Architecture

  • Base: Applio 3.6.2, RVC v2, HiFi-GAN vocoder, ContentVec embedder
  • Pretrain: TITAN Medium 32k (blaise-tk/TITAN)
  • F0: rmvpe
  • Sample rate: 32kHz mono

Training

  • Dataset: 537 clips, ~45 min total, 15 emotional categories
  • Hardware: RTX PRO 6000 Blackwell (96GB)
  • Hyperparameters: batch 16, 300 epochs, save every 25
  • Wall time: ~30 min
  • Best loss: g_loss 24.6 at epoch 50

Files

  • aiden_300e_19200s.pth — final epoch 300 checkpoint
  • aiden_300e_19200s_best_epoch.pth — best loss checkpoint
  • aiden.index — FAISS retrieval index for ContentVec features
  • config.json — training config
  • model_info.json — dataset metadata

Inference parameters (calibrated)

  • index_rate: 0.4-0.7 (higher = more Jaiden timbre, less source emotion)
  • protect: 0.33
  • volume_envelope (rms_mix_rate): 0.25
  • f0_method: rmvpe

Status

Trained 2026-05-06. Project subsequently pivoted to Kokoro/Chatterbox-only (without voice transfer step) — voice cloning to Jaiden's specific timbre wasn't a hard requirement. AIDEN preserved here as a reference / future option.

Sources

1 source
Hugging FacePrimaryVersion 37f51b0401e80165c5cf8f76cffd74a879e4aad9
huggingface.co/jeffhm14/aiden-v1/tree/37f51b0401e80165c5cf8f76cffd74a879e4aad9

Verified Oct 31

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

2 artifacts

aiden_300e_19200s_best_epoch.pth

pth · 53.6 MB · SHA-256 d9967287e247…271d · Hugging Face

Download file

aiden_300e_19200s.pth

pth · 53.6 MB · SHA-256 379e15a9dc51…5b80 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 14huggingface.co/jeffhm14/aiden-v1

--- license: mit tags: - rvc - voice-conversion - aiden - paion language: - en pipeline_tag: audio-to-audio --- # AIDEN — Acoustic Intonation Decoder + Expressive Neural Single-speaker RVC v2 model trained on Jaiden (17yo male) for the Paion project. ## Architecture - Base: Applio 3.6.2, RVC v2, HiFi-GAN vocoder, ContentVec embedder - Pretrain: TITAN Medium 32k (`blaise-tk/TITAN`) - F0: rmvpe - Sample rate: 32kHz mono ## Training - Dataset: 537 clips, ~45 min total, 15 emotional categories - Hardware: RTX PRO 6000 Blackwell (96GB) - Hyperparameters: batch 16, 300 epochs, save every 25 - Wall time: ~30 min - Best loss: g_loss 24.6 at epoch 50 ## Files - `aiden_300e_19200s.pth` — final epoch 300 checkpoint - `aiden_300e_19200s_best_epoch.pth` — best loss checkpoint - `aiden.index` — FAISS retrieval index for ContentVec features - `config.json` — training config - `model_info.json` — dataset metadata ## Inference parameters (calibrated) - index_rate: 0.4-0.7 (higher = more Jaiden timbre, less source emotion) - protect: 0.33 - volume_envelope (rms_mix_rate): 0.25 - f0_method: rmvpe ## Status Trained 2026-05-06. Project subsequently pivoted to Kokoro/Chatterbox-only (without voice transfer step) — voice cloning to Jaiden's specific timbre wasn't a hard requirement. AIDEN preserved here as a reference / future option.

NoteOct 31huggingface.co/jeffhm14/aiden-v1

Source context: 9 downloads · 0 likes · Pipeline audio-to-audio · Repo jeffhm14/aiden-v1

NoteAug 14huggingface.co/jeffhm14/aiden-v1

Source context: 8 downloads · 0 likes · Pipeline audio-to-audio · Repo jeffhm14/aiden-v1