Skip to content
View jonnyli1125's full-sized avatar

Highlights

  • Pro
Block or Report

Block or report jonnyli1125

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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
jonnyli1125/README.md

Hi there ๐Ÿ‘‹

I'm Jonny, a machine learning engineer at SoundHound AI. Interested in the engineering side of NLP and ML/AI things.

This is where I upload projects about topics I'm interested in!

  • โ›๏ธ Iโ€™m currently working on LLMs and automatic speech recognition
  • ๐Ÿ“ˆ Iโ€™m currently learning about low-level model inference optimization and Rust
  • ๐Ÿ’ฌ Ask me about anything related to linguistics or language learning
  • ๐Ÿ˜„ Pronouns: He/Him
  • โ™Ÿ๏ธ Fun fact: I love to play strategy board games (go, chess, etc.)

Anurag's GitHub stats

Pinned

  1. gector-ja gector-ja Public

    BERT-based GEC tagging for Japanese

    Python 12 2

  2. piemanese-translator piemanese-translator Public

    Webspeak to English statistical + neural hybrid machine translation model.

    Jupyter Notebook 1

  3. docs-assistant docs-assistant Public

    Question answering bot for documentation databases

    Python

  4. jp-srparser jp-srparser Public

    Shift reduce dependency parser for Japanese

    Jupyter Notebook

  5. RNN Transducer in ~100 lines of NumP... RNN Transducer in ~100 lines of NumPy code. Paper: https://arxiv.org/abs/1211.3711
    1
    from dataclasses import dataclass
    2
    import numpy as np
    3
    
                  
    4
    vocab = [None, 'a', 'b', 'c']
    5
    null_idx = 0
  6. Implementing and training a neural n... Implementing and training a neural network from scratch in numpy only
    1
    {
    2
      "nbformat": 4,
    3
      "nbformat_minor": 0,
    4
      "metadata": {
    5
        "colab": {