Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
A new open-source text-to-speech system, Indic-Parler TTS, has been launched, supporting 20 Indic languages. The system, developed in collaboration with AI4Bharat and Hugging Face, is trained on 10,000 hours of data and features 938 million parameters. It also includes emotional synthesis capabilities and is licensed under Apache 2.0. This initiative aims to provide accessible, high-quality speech synthesis for over a billion speakers of Indic languages. Additionally, a benchmark titled "Pralekha: An Indic Document Alignment Evaluation Benchmark" has been introduced, focusing on document-level alignment across 11 Indic languages.
Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with @huggingface, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality… https://t.co/g7xhFM2mYl
Very impressive Indic-Parler TTS - Trained on 10K hours of data, - 938M params - Supports 20 Indic languages, - Emotional synthesis - Apache 2.0 licensed Kudos to @ai4bharat and @huggingface H/t: @reach_vb https://t.co/Y0uNCrksHb
Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ @ai4bharat & @huggingface - w/ fully customisable speech and voice personas! Try it out directly below or use… https://t.co/8aagHcCT61
