Popular GitHub Repositories for Nemo

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Experiments to test different speech recognition systems for SEPIA Framework

Verifying the identity of a person from characteristics of the voice independent from language via NVIDIA NeMo models (ECAPA-TDNN, SpeakerNet, TitaNet-L).

This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.

This repository contains an attempt to utilize the NeMo toolkit created by NVIDIA

An end to end deep speech REST API containing speech to text and text speech services for Kinyarwanda.

Extendable toolkit for comprehensive evaluation of ASR systems. Currently supports benchmarking 29 system-models combination for Polish using BIGOS datasets.

ASR (Automatic Speech Recognition) Notebooks

SSAK contains helpers and tools to process data and train/infer ASR models.

a ASR(automatic speech recognition) model for Persian language based on QuartzNet15x5 from Nvidia Nemo

Notebooks for "AI ??-??"

This repository contains a sample text data-preparation code using Nemo Curator for pre-training or synthetic data generation