AshwinSankar17

MS DSAI @ Indian Institute of Technology Madras | AI4Bharat | Working in Speech x Multi-Modal AI.

AI4Bharat | Indian Institute of Technology, MadrasChennai

Pinned Repositories

IndicVoices-R
A Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
Language:Python34 8 71
AI4Bharat_TTS_Paper_Reading_Group
List of papers and optionally their summary covered in the TTS team's paper reading sessions at AI4Bharat
1 1 00
astravani
Weapons to wield sound
Language:Python1 1 00
DeepRL
Various algorithms implemented with CLI for easier training and testing purposes
Language:Python0 1 00
idle_time
Usage of module gives the idle time of the computer. Note: Linux requires xprintidle. Use "sudo apt install xprintidle" for the module to work.
Language:Python1 1 01
Mimi
Language:Python10
NewsCluster
Scrape and cluster news based on the headlines
Language:Jupyter Notebook1 1 82
ot-flow-matching-tts
Flow-matching DiT for speech editing and synthesis
Language:Jupyter Notebook10
Roar
Roar - a toolkit for Indic Speech AI
Language:Python00

AshwinSankar17's Repositories

AshwinSankar17/AI4Bharat_TTS_Paper_Reading_Group
List of papers and optionally their summary covered in the TTS team's paper reading sessions at AI4Bharat
1 1 00
AshwinSankar17/astravani
Weapons to wield sound
Language:Python1 1 00
AshwinSankar17/Mimi
Language:Python10
AshwinSankar17/ot-flow-matching-tts
Flow-matching DiT for speech editing and synthesis
Language:Jupyter Notebook10
AshwinSankar17/advice
A repository of links with advice related to grad school applications, research, phd etc
0 0 00
AshwinSankar17/Roar
Roar - a toolkit for Indic Speech AI
Language:Python00
AshwinSankar17/AshwinSankar17.github.io
Personal website using ai-folio
Language:HTML1 0
AshwinSankar17/attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
AshwinSankar17/Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
AshwinSankar17/conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
AshwinSankar17/DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
AshwinSankar17/Diff-HierVC
Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"
Language:Python0 0
AshwinSankar17/google-research
Google Research
Language:Jupyter Notebook
AshwinSankar17/HoMM
High order Moment Models
Language:Python0 0
AshwinSankar17/iamunr4v31
AshwinSankar17/lightning-hydra-template
Language:Python1 0
AshwinSankar17/moshi
AshwinSankar17/parler-tts
Inference and training library for high-quality TTS models.
Language:Python0 0
AshwinSankar17/penn
Pitch Estimating Neural Networks (PENN)
Language:Python0 0
AshwinSankar17/pyxis
Container plugin for Slurm Workload Manager
AshwinSankar17/rfpp
The codebase of our paper "Improving the Training of Rectified Flows"
AshwinSankar17/seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
Language:Jupyter Notebook
AshwinSankar17/StableTTS
Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
AshwinSankar17/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
AshwinSankar17/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
AshwinSankar17/TTS-data-pipeline
WiP: A TTS data scraping pipeline for youtube with music separation, denoising and auto-transcriptions
Language:Python
AshwinSankar17/VITS
Language:Python
AshwinSankar17/VITS_hf_port
Code to port VITS checkpoint to AutoModel compatible version.
Language:Python
AshwinSankar17/VoiceFlow-TTS
[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"
Language:Python0 0
AshwinSankar17/x-clip
A concise but complete implementation of CLIP with various experimental improvements from recent papers