# Plachtaa/VITS-fast-fine-tuning

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Repository: https://github.com/Plachtaa/VITS-fast-fine-tuning
Canonical: https://ross.abutalabs.com/products/vits-fast-fine-tuning
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2025-01-21T12:54:43+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 2, release rhythm 8, longevity 92
- inputs: {"age_days": 1300, "days_push": 589, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5012, forks 727 (observed 2026-08-28T04:09:04.662370+00:00)

## What it is
A Python pipeline for fast fine-tuning of VITS text-to-speech models, enabling speaker adaptation in under an hour from short audio, long audio, or video samples. It supports multilingual (English, Japanese, Chinese) TTS synthesis and many-to-many voice conversion between added and preset speakers.

## Use cases
- clone a character voice from a few short audio clips
- fine-tune a TTS model on my own voice
- convert voice between multiple speakers
- synthesize Chinese Japanese or English speech with custom voices
- extract voice from videos for TTS training
- train a voice model on Google Colab

## When to choose
- you want to add custom voices to a pretrained VITS TTS model quickly
- you need many-to-many voice conversion between speakers
- you have limited training data (10+ short clips or 3+ minutes of audio)
- you want multilingual TTS in English, Japanese, and Chinese

## When to avoid
- you need production-grade, low-latency TTS serving at scale
- you want to train a TTS model from scratch rather than fine-tune
- you need languages beyond English, Japanese, and Chinese
- you require real-time voice conversion with minimal latency

## Facets
- artifact type: library
- maturity: active
- function: tts, machine-learning, llm-training, audio-processing, speech-recognition
- domain: speech-processing, machine-learning, deep-learning, artificial-intelligence
- platform: python, cross-platform, windows
- tags: vits, voice-conversion, voice-cloning, fine-tuning, text-to-speech, speaker-adaptation, transfer-learning, audio, gpu, web-server

## Member repositories
- Plachtaa/VITS-fast-fine-tuning (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:04.662370+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:17:32.714163+00:00, confidence not recorded.
  - readme: https://github.com/Plachtaa/VITS-fast-fine-tuning (fetched 2026-08-28T04:09:04.662370+00:00, sha 36d910524813)
- Data as of 2026-08-30T08:39:29.467469+00:00.