This is your work, valued

Yatharth Sharma

Intermediate
@ysharma3501

Interested in machine learning such as speech generation/recognition, RAG, mcp, and agents.

LuxTTS. A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.

4.8k

NovaSR. A lightning fast audio upsampler.

772

LavaSR. 🌋LavaSR: Fast Speech restoration and enhancement

559

MiraTTS. A high quality and fast TTS repository

516

LinaCodec. A highly compressive and high-quality neural audio codec for speech models.

269

FlashSR. Fast audio super resolution from 16khz to 48khz.

216

FastNeuTTS. A highly optimized engine for neutts-air model to generate minutes of audio in seconds. Over 200x realtime on modern hardware!

118

FastMaya. A highly optimized engine for maya-1 tts model to generate minutes of audio in seconds.

65

LayaCodec. High fidelity neural audio codec for TTS models

36

FastBiCodec. Fast version of BiCodec tokenizer and FlashSR model

10

ysharma3501. Readme for Ysharma3501

2