Yatharth Sharma

YaTharThShaRma999's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 13 hours ago

YaTharThShaRma999/LavaSR

Updated about 13 hours ago • 21

published a model 5 days ago

YaTharThShaRma999/LavaSR

Updated about 13 hours ago • 21

liked a model 18 days ago

YatharthS/LuxTTS

Text-to-Speech • Updated 19 days ago • 1.77k • 125

liked a Space 18 days ago

Running

Featured

57

LuxTTS

🚀

57

Space for LuxTTS: a 150x realtime voice cloning TTS model

liked a Space 29 days ago

Running

Featured

78

NovaSR

🐢

78

An incredibly fast and tiny audio upsampler

published a Space 29 days ago

Sleeping

Novasr

🔥

s

updated a Space 29 days ago

Sleeping

Novasr

🔥

s

liked a model 29 days ago

YatharthS/NovaSR

Audio-to-Audio • Updated 23 days ago • 829 • 76

liked a model about 1 month ago

YatharthS/LinaCodec

Audio-to-Audio • Updated Jan 3 • 138 • 22

updated a model about 1 month ago

YaTharThShaRma999/ncodec

Updated Dec 31, 2025

updated a model about 2 months ago

YaTharThShaRma999/miratts_finetune

Text Generation • 0.5B • Updated Dec 21, 2025 • 2

published a model about 2 months ago

YaTharThShaRma999/miratts_finetune

Text Generation • 0.5B • Updated Dec 21, 2025 • 2

reacted to YatharthS's post with 🚀🔥 about 2 months ago

view post

Post

3692

🤯 🤯 Released a high quality finetuned LLM based TTS model that can generate realistic and clear 48khz audio at over 100x realtime speed! 🤯 🤯

Github link: https://github.com/ysharma3501/MiraTTS

Model link: https://github.com/ysharma3501/MiraTTS

Blog explaining llm tts models: https://huggingface.co/blog/YatharthS/llm-tts-models

See translation

• 
• 
• 
• 4 replies

·

🔥

10

10

🚀

6

6

👍

3

3

+

Reply

upvoted an article about 2 months ago

view article

Article

LLM based Audio models

• 

Dec 18, 2025

•

49

liked a model about 2 months ago

YatharthS/MiraTTS

Text-to-Speech • 0.5B • Updated Dec 24, 2025 • 2.84k • 185

updated a model about 2 months ago

YaTharThShaRma999/vocos_lib2

Updated Dec 17, 2025

reacted to YatharthS's post with 🚀🔥 about 2 months ago

view post

Post

2836

I just released LayaCodec, a highly efficient neural audio tokenizer/codec for TTS models, far better than most previous audio tokenizers.

🤯 Next-gen TTS models that use this could achieve several 100s of times real-time speed while producing clearer audio!! 🤯

GitHub repo: https://github.com/ysharma3501/LayaCodec
Model: YatharthS/LayaCodec

See translation

🔥

6

6

🚀

3

3

+

Reply

New activity in YatharthS/LayaCodec about 2 months ago

Update README.md

#1 opened about 2 months ago by

YaTharThShaRma999