persian-tts-female-vits

• persian-tts-female vits model for text to speech purposes.
• Persian فارسی
• Single-speaker female voice
• Trained on persian-tts-dataset-male dataset
• GitHub Repo
• Demo

Uses

Install dependencies:

!pip install TTS
!sudo apt-get -y install espeak-ng

Generate audio from text:

using cli:

!tts --text "زندگی فقط یک بار است؛ از آن به خوبی استفاده کن" \
     --model_path ".pth" \
     --config_path "config.json" \
     --out_path "speech1.wav"

python api:

from TTS.config import load_config
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer

config="config.json" 
model="best_model_30824.pth"

model_path =model # Absolute path to the model checkpoint.pth
config_path =config # Absolute path to the model config.json

text=".زندگی فقط یک بار است؛ از آن به خوبی استفاده کن"

synthesizer = Synthesizer(
    model_path, config_path
)
wavs = synthesizer.tts(text)
synthesizer.save_wav(wavs, 'sp.wav')

Display audio:

import IPython
IPython.display.Audio('sp.wav')

• Hours used: 10
• Cloud Provider: kaggle

How to Get Started with the Model

Use the code below to get started with the model.