🌐 中文 English
This article aims to introduce how to deploy the IndexTTS model on the Windows platform.
What is IndexTTS
IndexTTS is the latest open-source voice generation model from Alibaba, capable of synthesizing different human voices by inputting different voice libraries and text.
Deploying IndexTTS
Open a terminal and clone the code repository:
1
git clone https://github.com/index-tts/index-tts.git
Navigate into the IndexTTS project repository, then open a terminal and enter the following commands:
1
2
3
conda create -n index-tts python=3.10
conda activate index-tts
pip install -r requirements.txt
When deploying on the Windows platform, using pip install -r requirements.txt may encounter the following issue:
1
2
3
Successfully built jieba encodec antlr4-python3-runtime distance
Failed to build pynini
ERROR: Failed to build installable wheels for some pyproject.toml based projects (pynini)
The solution is (note: you must first execute pip install -r requirements.txt to install other dependencies):
1
2
3
conda install -c conda-forge pynini==2.1.5
pip install WeTextProcessing==1.0.3
pip install -e ".[webui]"
Download the models (this requires internet access and must be done by opening a terminal in the root directory of the project repository and entering the following commands):
1
2
3
4
5
6
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/bigvgan_discriminator.pth -P checkpoints
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/bigvgan_generator.pth -P checkpoints
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/bpe.model -P checkpoints
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/dvae.pth -P checkpoints
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/gpt.pth -P checkpoints
wget https://huggingface.co/IndexTeam/Index-TTS/resolve/main/unigram_12000.vocab -P checkpoints
Using IndexTTS
Open a terminal in the root directory of the project repository and enter the following command:
1
python webui.py
It will return a link by default during runtime, as shown below:
1
2
>> TextNormalizer loaded
* Running on local URL: http://127.0.0.1:7860
Copy and paste http://127.0.0.1:7860 into your browser to access the IndexTTS webui interface.
Then, input text, select a voice library, click generate, and the corresponding human voice will be synthesized.
