Mayank Sinha's repositories
bark
π Text-Prompted Generative Audio Model
candle
Minimalist ML framework for Rust
cpython
The Python programming language
CTranslate2
Fast inference engine for Transformer models
leetcode-solutions
A repository containing solutions to leetcode problems
llm-lora-finetune
Repo to train llama2 using lora and peft, using a gui app.
efficientspeech
PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.
fastapi
FastAPI framework, high performance, easy to learn, fast to code, ready for production
faster-whisper
Faster Whisper transcription with CTranslate2
hyprdots
// Aesthetic, dynamic and minimal dots for Arch hyprland
llama2.c
Inference Llama 2 in one file of pure C
LongLoRA
Code and documents of LongLoRA and LongAlpaca
mayanksinha900.github.io
Personal Portfolio
model-architectures
A repo that will contain architecture from different machine learning papers, both in keras and pytorch
MS-SNSD
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired.
NeMo
NeMo: a toolkit for conversational AI
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Shepherd
This is the repo for the paper Shepherd -- A Critic for Language Model Generation
StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
transformers
π€ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
triton
Development repository for the Triton language and compiler
TTS
πΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
vocode-python
π€ Build voice-based LLM agents. Modular + open source.
voice_datasets
π A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
VoiceCraft
Zero-Shot Speech Editing and Text-to-Speech in the Wild