remsky / text-to-speech Open weights updated 1 week ago

kokoro-inno-clone-tuner

Name: kokoro-inno-clone-tuner
Author: remsky

Same passage for every voice, enrolled from the references. LibriTTS-R speakers are dev-clean held out from training.

Params

9.7 M

Context

—

Downloads 30d

1.2 M

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 27 days

1.2 M417 K

Sep 26Oct 5Oct 14Oct 22

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f16	0.0 GB	0.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Parameters: 9.7 M
Tensor type: F16
Licence: apache-2.0
First seen on the Hub: 2026-08-31
Base model: Kokoro-82M
Training datasets: parler-tts/libritts_r_filtered, facebook/voxpopuli, amphion/Emilia-Dataset
Added to our catalog: 2026-09-26

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-to-speech model

Popular comparisons

Appears in

Best open-source TTS