Skip to content
View shigabeev's full-sized avatar
🥐
🥐

Highlights

  • Pro

Block or report shigabeev

Report abuse

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

Report abuse
shigabeev/README.md

Hi there, I'm Ilya Shigabeev 👋

I am a Machine learning engineer with focus on Speech technologies such as speaker recognition and text-to-speech as well as voice cloning. I don't contribute to open source much.

  • 🔭 I’m currently working on video translation app langswap.app. We are using cutting-edge technologies in text-to-speech, automatic speech recognition and translation to build it.
  • 💬 Ask me about Machine learning and voice technology in particular.
  • 📫 How to reach me: @frappuccino_o pretty much everywhere.https://t.me/frappuccino_o,
  • 💌 My telegram channel about voice tech: https://t.me/voicestuff
  • 📸 My Instagram https://instagram.com/frappuccino_o

Pinned Loading

  1. langswap-app/langswap langswap-app/langswap Public

    Self-hosted AI video dubbing with ASR, translation, voice cloning, subtitles, and local GPU inference.

    Python 31 5

  2. russian_tts_normalization russian_tts_normalization Public

    Fast Russian Text normalization for TTS using only RegEx.

    Python 32 3

  3. address-normalizer address-normalizer Public

    Ищет выбранный адрес в ФИАС

    Python 40 6

  4. vits2_pytorch_bigvgan vits2_pytorch_bigvgan Public

    Forked from p0p4k/vits2_pytorch

    unofficial vits2-TTS implementation in pytorch

    Python 6

  5. Q-VITS2-Voice-Cloning Q-VITS2-Voice-Cloning Public

    Forked from FENRlR/MB-iSTFT-VITS2

    WIP: VITS 2 with quantized output of text-encoder and voice cloning

    Python 6 4

  6. stretch_audio stretch_audio Public

    Pretty decent algorithm to stretch audio with far less artifacts than WSOLA/librosa.

    Python 9