Popular GitHub Repositories for Nvidia Nemo

Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan

Extractive Question-Answering with BERT on SQuAD v2.0 (Stanford Question Answering Dataset) using NVIDIA PyTorch Lightning

Post-training quantization on Nvidia Nemo ASR model

This repository combines `WavLM`, a powerful speech representation model from Microsoft, with `MSDD` (Multi-Scale Diarization Decoder), a state-of-the-art approach for speaker diarization from Nvidia.

? SmartSRT is a command-line tool for generating accurate subtitles with per-word timestamps. It uses WhisperAI for speech transcription, NVIDIA NeMo for diarization, and OpenCV for face recognition. The program is good at creating high accuracy subtitles. ??⚙️

This bootcamp is designed to give NLP researchers an end-to-end overview on the fundamentals of NVIDIA NeMo framework, complete solution for building large language models. It will also have hands-on exercises complimented by tutorials, code snippets, and presentations to help researchers kick-start with NeMo LLM Service and Guardrails.

Implementation of a Kazakh Speech-to-Text Model using the NVIDIA NeMo toolkit for efficient transcription of spoken Kazakh speech into text.