Skip to content
View shivammehta25's full-sized avatar
:octocat:
this animal in his natural habitat
:octocat:
this animal in his natural habitat
175 followers · 198 following

Achievements

Achievement: Starstruckx3Achievement: YOLOAchievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: Starstruckx3Achievement: YOLOAchievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Highlights

  • Pro

Block or report shivammehta25

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shivammehta25/README.md

Hello I am Shivam Mehta

I am a Researcher in Department of Speech Music and Hearing at KTH Royal Institute of Technology!

🎯 Currently, I am in Menlo Park, WA as a Research Scientist Intern at Meta.
🎯 Summer 2024 I was in Seattle, WA as a Research Intern at Microsoft Research.
🔭 I work on Speech synthesis with probabilistic generative models
💬 Ask me about: Python, Deep Learning, Machine Learning and Generative modelling
📫 Reach me or read my blog at: https://shivammehta25.github.io/
💬 Open for collaborations and interesting projects!

My recent works:
⚡ MAGI: Multimodal Audio and Gesture, Integrated: https://shivammehta25.github.io/MAGI/
⚡ 🍵 Matcha-TTS: https://shivammehta25.github.io/Matcha-TTS/
⚡ Unified speech and gesture synthesis using flow matching: https://shivammehta25.github.io/Match-TTSG/
⚡ Diff-TTSG: https://shivammehta25.github.io/Diff-TTSG/
⚡ OverFlow: https://shivammehta25.github.io/OverFlow
⚡ Neural HMM TTS: https://shivammehta25.github.io/Neural-HMM

GitHub Stats:


Pinned Loading

  1. Matcha-TTS Matcha-TTS Public

    [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

    Jupyter Notebook 736 91

  2. Neural-HMM Neural-HMM Public

    Neural HMMs are all you need (for high-quality attention-free TTS)

    Jupyter Notebook 156 23

  3. OverFlow OverFlow Public

    Putting flows on top of neural transducers for better TTS

    Jupyter Notebook 63 10

  4. BetterFastSpeech2 BetterFastSpeech2 Public

    Just another FastSpeech 2 but cleaner code :)

    Jupyter Notebook 25 2

  5. coqui-ai/TTS coqui-ai/TTS Public

    🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

    Python 35.4k 4.3k

  6. Diff-TTSG Diff-TTSG Public

    Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis

    Python 37 2