Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
coqui-tts/recipes/ljspeech/xtts_v2/README.md

1.2 KiB
Raw Blame History

Coqui AI TTS

This repository contains the code for training a text-to-speech (TTS) model using Coqui AI's TTS framework.

Installation and Configuration

  1. Clone the repository:

    git clone https://github.com/owos/coqui-ai-TTS.git

  2. Navigate to the repository root:

    cd coqui-ai-TTS

  3. Install system dependencies and the code:

    make system-deps  # Intended to be used on Ubuntu (Debian). Let us know if you have a different OS.
make install

  4. Open the following file and redefine the specified variables:

    File: recipes/ljspeech/xtts_v2/train_gpt_xtts.py

    # Line 30
path = 'the root path to the audio dirs on your machine'

# Line 31
meta_file_train = "the root path to the train CSV on your machine"

# Line 32
meta_file_val = "the root path to the train CSV on your machine"

# Line 75
SPEAKER_REFERENCE = "a list with a single path to a test audio from the afro tts data"

Running the Code

From the repository root, run the following command:

python3 recipes/ljspeech/xtts_v2/train_gpt_xtts.py

You are now ready to train your TTS model using Coqui AI's framework. Enjoy!