Kamtera's picture
Update README.md
da238d6
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-male-vits

info

finetuned persian-tts-female-vits model on persian-tts-dataset-male dataset

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 "best_model_91323.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_91323.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