Akash Mahajan's repositories
cs224n-gpu-that-talks
Attention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)
cs341-ibm-seti
Classifying signals and simulations representing data from the Allen Telescope Array (ATA)
spotify-top200-breakdown
Project done for MS&E226 - taught by Prof. Ramesh Johari
akashmjn.github.io
Personal website
akashmjn.github.io-old
Personal website
CNTK
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
cs221-iMGM
Repository for CS221 project - Improved Music Generation with Magenta
cs230-starter-code
Project Starter Code for CS230
pytorch-kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
dotfiles
My Global configuration files. Vim, Bash, gitignore, Rstudio etc.
gitignore
A collection of useful .gitignore templates
kaldi
Personal fork from the official location of the Kaldi project at
magenta
Magenta: Music and Art Generation with Machine Intelligence
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
onnx
Open standard for machine learning interoperability
podcast
Temp space for Orcasound ML efforts
pretty-midi
Utility functions for handling MIDI data in a nice/intuitive way.
tacotron
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model
torch7
http://torch.ch
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.