Overview
Why NeMo Framework?
Software Component Versions
Getting Started
Playbooks
Cloud Service Providers
SFT and PEFT
RAG
Large Language Models
Embedding Models
Multimodal Models
Speech AI Models
Deploy NeMo Framework Models
Library Documentation
NeMo
Introduction
Tutorials
Mixed Precision Training
Parallelisms
Memory Optimizations
Throughput Optimizations
Community Checkpoint Converter
NeMo APIs
NeMo Collections
Speech AI Tools
NeMo Forced Aligner (NFA)
Dataset Creation Tool Based on CTC-Segmentation
Speech Data Explorer
Comparison tool for ASR Models
ASR Evaluator
Speech Data Processor
(Inverse) Text Normalization
WFST-based (Inverse) Text Normalization
Neural Models for (Inverse) Text Normalization
Neural Text Normalization Models
Thutmose Tagger: Single-pass Tagger-based ITN Model
NeMo Framework Launcher
NeMo Aligner
NeMo Curator
Example Scripts for Pretraining and Fine-tuning
Changelog
Known Issues
NVIDIA NeMo Framework User Guide
»
Library Documentation
»
NVIDIA NeMo Framework Developer Docs
»
Speech AI Tools
»
(Inverse) Text Normalization
»
Neural Models for (Inverse) Text Normalization
Neural Models for (Inverse) Text Normalization
NeMo provides two types of neural models:
Duplex T5-based TN/ITN:
Neural Text Normalization Models
Single-pass Tagger-based ITN:
Thutmose Tagger: Single-pass Tagger-based ITN Model