Name: Karthik Ganesan
Type: User
Company: ML Researcher @ nexusflow.ai
Bio: ML Research @ Nexusflow.ai.
Previously : Amazon Alexa, CMU Speech WavLab
CMU SCS Alum
Location: Sanfrancisco, USA
Blog: https://www.linkedin.com/in/karthik-ganesan-b07462124/
Karthik Ganesan's Projects
BOT Framework style custom web chat for api.ai agent.
An Open-source Streaming High-fidelity Neural Audio Codec
This repo has code base thats a fusion of BOLAA and Webarena to be build hyper-personalized agents that are aligned to your life-goals
coding interview brushup
A TensorFlow implementation of Baidu's DeepSpeech architecture
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
End-to-End Speech Processing Toolkit
Onnx wrapper for espnet infrernce model
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
The repository contains the code for the various machine learning algorithms used to make a predictive analysis of tweets on GST in India The Goods and Services Tax has been a revolutionary change in the financial standards of India
:mag: Transformers at scale for question answering & search
Discovering and Achieving Goals via World Models, NeurIPS 2021
Generate SQUAD style dataset from raw text file and train a transformer based question answering model .This repo has code from https://github.com/facebookresearch/UnsupervisedQA and https://github.com/deepset-ai/haystack
Code and documents of LongLoRA and LongAlpaca
Machine Learning at Vernacular.ai
[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning
This repository contains files related to a new channel website built as a part of
NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.
Voice data <= 10 mins can also be used to train a good VC model!