parlertts-multi-indic

A Indic Parler-TTS model by AI4Bharat, from ai4bharat/indic-parler-tts, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture Indic Parler-TTS
Upstream ai4bharat/indic-parler-tts
Author AI4Bharat
Languages as, bn, brx, doi, en-IN, gu, hi, hne, kn, ml, mni, mr, ne, or, pa, sa, ta, te
Text input Unicode codepoints of the text

How to use

pip install --pre phoonnx
import wave
from phoonnx.model_manager import TTSModelManager

manager = TTSModelManager()
manager.load()
manager.merge_default_voices()

voice = manager.voices["indic_parler/aditi/bn"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in bn
    voice.synthesize_wav(text, wav_file)

In OVOS, phoonnx installs the ovos-tts-plugin-phoonnx plugin. Select the voice in mycroft.conf:

{"tts": {"module": "ovos-tts-plugin-phoonnx", "ovos-tts-plugin-phoonnx": {"voice": "indic_parler/aditi/bn"}}}

Text front end

phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:

  • unicode: UnicodeCodepointPhonemizer from scriptconv.phonemizers.base, in scriptconv itself.

phoonnx voices

  • indic_parler/aditi/bn
  • indic_parler/amit/as
  • indic_parler/amrita/ne
  • indic_parler/anjali/ml
  • indic_parler/anu/kn
  • indic_parler/arjun/bn
  • indic_parler/aryan/sa
  • indic_parler/bhanu/hne
  • indic_parler/bikram/brx
  • indic_parler/champa/hne
  • indic_parler/debjani/or
  • indic_parler/divjot/pa
  • indic_parler/divya/hi
  • indic_parler/gurpreet/pa
  • indic_parler/harish/ml
  • indic_parler/jaya/ta
  • indic_parler/karan/doi
  • indic_parler/laishram/mni
  • indic_parler/lalitha/te
  • indic_parler/manas/or
  • indic_parler/mary/en
  • indic_parler/maya/brx
  • indic_parler/neha/gu
  • indic_parler/prakash/te
  • indic_parler/ranjit/mni
  • indic_parler/rohit/hi
  • indic_parler/sanjay/mr
  • indic_parler/sita/as
  • indic_parler/sunita/mr
  • indic_parler/suresh/kn
  • indic_parler/thoma/en
  • indic_parler/yash/gu

Licence

The upstream declares the licence apache-2.0 in the model card of ai4bharat/indic-parler-tts.

Related projects

  • phoonnx: runs this model, in Python and in OVOS.
  • scriptconv: text normalisation, script conversion and phonemizers for phoonnx.
  • The Indic Parler-TTS collection: every Indic Parler-TTS model packaged for phoonnx.
Downloads last month
608
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including Phoonnx/parlertts-multi-indic