country_code
Skip to main content
Ctrl+K
NeMo-Speech - Home NeMo-Speech - Home

NeMo-Speech

  • GitHub
NeMo-Speech - Home NeMo-Speech - Home

NeMo-Speech

  • GitHub

Table of Contents

Getting Started

  • Installation
  • NeMo Speech Inference in 5 Minutes
  • Key Concepts in Speech AI
  • Choosing a Model
  • Tutorials

Training

  • Parallelisms
  • Mixed Precision Training
  • Checkpoint Formats
  • Lhotse Dataloading

Collections

  • Automatic Speech Recognition (ASR)
    • Featured Models
    • ASR Model Checkpoints
    • Inference
    • Fine-Tuning
    • Datasets
    • ASR Language Modeling and Customization
      • NGPU-LM (GPU-based N-gram Language Model) Language Model Fusion
      • Neural Rescoring
      • N-gram Language Model Fusion
      • Scripts for building and merging N-gram Language Models
      • Word Boosting
    • NeMo ASR Configuration Files
    • NeMo ASR API
    • Featured Community Checkpoints
  • Text-to-Speech (TTS)
    • Models
    • Data Preprocessing
    • Checkpoints
    • NeMo TTS Configuration Files
    • Grapheme-to-Phoneme Models
    • Magpie-TTS
    • Magpie-TTS Finetuning
    • Magpie-TTS Preference Optimization
    • Magpie-TTS Longform Inference
  • SpeechLM2
    • Models
    • Datasets
    • Configuration Files
    • Training and Scaling
  • Speaker Diarization
    • Models
    • Datasets
    • Checkpoints
    • Speaker Diarization Configuration Files
    • NeMo Speaker Diarization API
    • Resource and Documentation Guide
  • Speaker Recognition (SR)
    • Models
    • NeMo Speaker Recognition Configuration Files
    • Datasets
    • Checkpoints
    • NeMo Speaker Recognition API
    • Resource and Documentation Guide
  • Speech and Audio Processing
    • Models
    • Datasets
    • Checkpoints
    • NeMo Audio Configuration Files
    • NeMo Audio API
  • Speech Self-Supervised Learning
    • Models
    • Datasets
    • Checkpoints
    • NeMo SSL Configuration Files
    • NeMo SSL collection API
    • Resources and Documentation
  • Speech Classification
    • Models
    • Datasets
    • Checkpoints
    • NeMo Speech Classification Configuration Files
    • Resource and Documentation Guide

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

APIs

  • NeMo Models
  • Neural Modules
  • Experiment Manager
  • Neural Types
  • Adapters
    • Adapter Components
    • Adapters API
  • NeMo Core APIs
  • NeMo Common Collection API
    • Callbacks
    • Losses
    • Metrics
    • Tokenizers
    • Data
    • S3 Checkpointing
  • NeMo ASR API
  • NeMo TTS API
  • NeMo Audio API
  • Speech Data Processor
Is this page helpful?

Speech Data Processor#

Speech Data Processor (SDP) is a toolkit to make it easy to:
  1. write code to process a new dataset, minimizing the amount of boilerplate code required.

  2. share the steps for processing a speech dataset.

SDP is hosted here: https://github.com/NVIDIA/NeMo-speech-data-processor.

To learn more about SDP, please check the [documentation](https://nvidia.github.io/NeMo-speech-data-processor/).

previous

ASR Evaluator

next

NeMo Models

NVIDIA NVIDIA
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.