Install Indic Parler-TTS model Locally

 This video shows how to locally install Indic Parler-TTS which can officially speak in 20 Indic languages.

Code:

conda create -n ai python=3.11 -y && conda activate ai

sudo apt-get install libportaudio2

conda install -c anaconda pyaudio

pip install torch torchaudio einops timm pillow

pip install git+https://github.com/huggingface/transformers

pip install git+https://github.com/huggingface/accelerate

pip install git+https://github.com/huggingface/diffusers

pip install huggingface_hub

pip install sentencepiece bitsandbytes protobuf decord

pip install librosa peft numpy

pip install git+https://github.com/huggingface/parler-tts.git

conda install -c conda-forge --override-channels notebook -y

conda install -c conda-forge --override-channels ipywidgets -y

jupyter notebook

import torch

from parler_tts import ParlerTTSForConditionalGeneration

from transformers import AutoTokenizer

import soundfile as sf

device = "cuda:0" if torch.cuda.is_available() else "cpu"

model = ParlerTTSForConditionalGeneration.from_pretrained("ai4bharat/indic-parler-tts").to(device)

tokenizer = AutoTokenizer.from_pretrained("ai4bharat/indic-parler-tts")

description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)

prompt = "अरे, तुम आज कैसे हो?"

description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."

input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)

prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)

audio_arr = generation.cpu().numpy().squeeze()

sf.write("indic_tts_out.wav", audio_arr, model.config.sampling_rate)