metadata
library_name: TTS
task: text-to-speech
tags:
- Persian
- TTS
- Farsi
- Coqui
- CoquiTTS
- pytorch
- audio
- text-to-speech
language: fa
datasets:
- persian-tts-dataset
widget:
- text: .زندگی فقط یک بار است؛ از آن به خوبی استفاده کن
example_title: Hello, this is a test run.
license: openrail
pipeline_tag: text-to-speech
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.
Click to expand
More information needed