Indicf5

🚀 IndicF5: High-Quality Text-to-Speech for Indian Languages

IndicF5 is a near-human polyglot Text-to-Speech (TTS) model that offers high - quality speech synthesis for 11 Indian languages, trained on extensive high - quality speech data.

🚀 Quick Start

IndicF5 is a high - performance TTS model trained on 1417 hours of high - quality speech from Rasa, IndicTTS, LIMMITS, and IndicVoices - R. It supports 11 Indian languages, including Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu.

📦 Installation

conda create -n indicf5 python=3.10 -y
conda activate indicf5
pip install git+https://github.com/ai4bharat/IndicF5.git

💻 Usage Examples

Basic Usage

To generate speech, you need to provide three inputs:

1. Text to synthesize – The content you want the model to speak.
2. A reference prompt audio – An example speech clip that guides the model’s prosody and speaker characteristics.
3. Text spoken in the reference prompt audio – The transcript of the reference prompt audio.

from transformers import AutoModel
import numpy as np
import soundfile as sf

# Load IndicF5 from Hugging Face
repo_id = "shethjenil/IndicF5"
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)

# Generate speech
audio = model(
    "नमस्ते! संगीत की तरह जीवन भी खूबसूरत होता है, बस इसे सही ताल में जीना आना चाहिए.",
    ref_audio_path="prompts/PAN_F_HAPPY_00001.wav",
    ref_text="ਭਹੰਪੀ ਵਿੱਚ ਸਮਾਰਕਾਂ ਦੇ ਭਵਨ ਨਿਰਮਾਣ ਕਲਾ ਦੇ ਵੇਰਵੇ ਗੁੰਝਲਦਾਰ ਅਤੇ ਹੈਰਾਨ ਕਰਨ ਵਾਲੇ ਹਨ, ਜੋ ਮੈਨੂੰ ਖੁਸ਼ ਕਰਦੇ  ਹਨ।"
)

# Normalize and save output
if audio.dtype == np.int16:
    audio = audio.astype(np.float32) / 32768.0
sf.write("namaste.wav", np.array(audio, dtype=np.float32), samplerate=24000)
print("Audio saved succesfully.")

You can find example prompt audios used here.

📚 Documentation

Datasets