Jaskaran Singh's repositories
audio_clip_processing_pipeline
Audio Clips Processing Pipeline
ENG-HIN-Machine-Translation
Translating Eng sentences into Hindi Using NLP and SEQ2SEQ model..
Opinion-Summarization
Research Project based on Abstract Opinion Summarization .
audioldm_eval
This toolbox aims to unify audio generation model evaluation for easier comparison.
bark
🔊 Text-Prompted Generative Audio Model
bddm
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
BigVGAN
Official PyTorch implementation of BigVGAN (ICLR 2023)
descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1 kHz mono/stereo audio.
encodec
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
NeMo
NeMo: a toolkit for conversational AI
phonemizer
Simple text to phones converter for multiple languages
seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
Sentimental_Extraction
About Bert Based approach to solve the kaggle challenge tweet-sentiment-extraction implemented in Tensorflow pipeline , Using high level Keras API . The solution was able to achieve 70.5% accuracy with 5-folds.
Symptom-Disease-Ordering
This Disease Predictor app helps user to identify a disease in real time by answering the various questions . The symptoms selected are then processed to take out the chances of a few particular ailments. Flask,NLP,Unsupervised Clustering.
textlesslib
Library for Textless Spoken Language Processing
torchcrepeV2
My own version of crepe, SOTA pitch tracking tool in PyTorch.
tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
tts-scores
Scripts for computing the Intelligibility and CLVP scores for evaluating TTS models
vocos
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
WhisperSpeech
An Open Source text-to-speech system built by inverting Whisper.