{"name":"NVIDIA NeMo Speech: Scalable Generative AI for Speech Models","description":"NVIDIA NeMo Speech is a powerful, scalable generative AI framework designed for researchers and developers focused on Large Language Models, Multimodal, and Speech AI. It provides tools for Automatic Speech Recognition (ASR) and Text-to-Speech (TTS), enabling efficient creation, customization, and deployment of new AI models using existing code and pre-trained checkpoints. This framework supports a wide range of applications, from real-time streaming ASR to high-quality multilingual TTS.","github":"https://github.com/NVIDIA-NeMo/Speech","url":"https://osrepos.com/repo/nvidia-nemo-speech","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/nvidia-nemo-speech","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/nvidia-nemo-speech.md","json":"https://osrepos.com/repo/nvidia-nemo-speech.json","topics":["asr","tts","generative-ai","deeplearning","python","speech-ai","llm","neural-networks"],"keywords":["asr","tts","generative-ai","deeplearning","python","speech-ai","llm","neural-networks"],"stars":null,"summary":"NVIDIA NeMo Speech is a powerful, scalable generative AI framework designed for researchers and developers focused on Large Language Models, Multimodal, and Speech AI. It provides tools for Automatic Speech Recognition (ASR) and Text-to-Speech (TTS), enabling efficient creation, customization, and deployment of new AI models using existing code and pre-trained checkpoints. This framework supports a wide range of applications, from real-time streaming ASR to high-quality multilingual TTS.","content":"## Introduction\n\nNVIDIA NeMo Speech is a comprehensive generative AI framework tailored for researchers and PyTorch developers working on advanced speech models. This includes Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and Speech Large Language Models (LLMs). The framework is engineered to streamline the process of creating, customizing, and deploying new AI models by leveraging existing code and a rich collection of pre-trained model checkpoints. It supports a wide range of applications, from real-time streaming ASR to high-quality multilingual TTS.\n\n## Installation\n\nNeMo Speech offers flexible installation options, allowing users to integrate it with their preferred Python, PyTorch, and CUDA versions.\n\n### From source with uv (recommended)\n\nFor a reproducible setup with the actively-tested stack (Python 3.13, PyTorch 2.12, CUDA 13.2), `uv` is the recommended installer.\n\nbash\ngit clone https://github.com/NVIDIA-NeMo/NeMo.git\ncd NeMo\nuv sync --extra all --extra cu13     # For CUDA 13.x (recommended)\n# Use --extra cu12 for CUDA 12.x\n\n\nThis installs NeMo into a `.venv/` in editable mode.\n\n### From PyPI with pip (fallback, bring your own versions)\n\nIf you prefer to use your own Python/PyTorch/CUDA stack, install PyTorch first (version ? 2.7), then install `nemo-toolkit` via `pip` or `uv pip`.\n\nbash\nuv pip install 'nemo-toolkit[asr,tts]'   # or plain: pip install 'nemo-toolkit[asr,tts]'\n\n\nTo pull NVIDIA's pinned PyTorch build, add the CUDA extra and the matching wheel index:\n\nbash\npip install 'nemo-toolkit[asr,tts,cu13]' --extra-index-url https://download.pytorch.org/whl/cu132   # CUDA 13.x\npip install 'nemo-toolkit[asr,tts,cu12]' --extra-index-url https://download.pytorch.org/whl/cu126   # CUDA 12.x\n\n\n## Examples\n\nNVIDIA NeMo Speech provides a rich set of pre-trained models and demos to get started quickly. You can explore various models for ASR, TTS, and Speech LLMs.\n\n*   **HuggingFace Collection**: Discover the latest open-weight checkpoints and interactive demos on the official [NVIDIA NeMo HuggingFace collection](https://huggingface.co/collections/nvidia/nemotron-speech){:target=\"_blank\"}.\n*   **Documentation**: The [NeMo Framework User Guide](https://docs.nvidia.com/nemo/speech/nightly/){:target=\"_blank\"} offers comprehensive technical documentation, including tutorials and examples for implementing different speech models.\n*   **Specific Demos**: Look for demos like [Nemotron 3 VoiceChat](https://build.nvidia.com/nvidia/nemotron-voicechat){:target=\"_blank\"} for full-duplex conversations or [Nemotron-Speech-Streaming](https://huggingface.co/spaces/nvidia/nemotron-speech-streaming-en-0.6b){:target=\"_blank\"} for real-time ASR.\n\n## Why Use NVIDIA NeMo Speech?\n\nNVIDIA NeMo Speech stands out as a robust framework for several reasons:\n\n*   **Scalability**: Built for large-scale generative AI, it supports complex models and high-throughput applications.\n*   **Comprehensive Features**: It covers a broad spectrum of speech AI tasks, including ASR, TTS, and multimodal LLMs.\n*   **Efficiency**: Designed to help researchers and developers efficiently create, customize, and deploy new AI models.\n*   **Pre-trained Models**: Access to a vast collection of pre-trained model checkpoints accelerates development and experimentation.\n*   **Flexibility**: Works with your chosen Python, PyTorch, and CUDA versions, offering adaptability to existing environments.\n*   **Active Development**: The project is actively maintained by NVIDIA, ensuring continuous updates and support for cutting-edge research.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/NVIDIA-NeMo/Speech](https://github.com/NVIDIA-NeMo/Speech){:target=\"_blank\"}\n*   **Official Documentation**: [https://docs.nvidia.com/nemo/speech/nightly/](https://docs.nvidia.com/nemo/speech/nightly/){:target=\"_blank\"}\n*   **HuggingFace Collection**: [https://huggingface.co/collections/nvidia/nemotron-speech](https://huggingface.co/collections/nvidia/nemotron-speech){:target=\"_blank\"}\n*   **Contributing Guide**: [https://github.com/NVIDIA-NeMo/NeMo/blob/main/CONTRIBUTING.md](https://github.com/NVIDIA-NeMo/NeMo/blob/main/CONTRIBUTING.md){:target=\"_blank\"}","metrics":{"detailViews":3,"githubClicks":1},"dates":{"published":null,"modified":"2026-07-12T00:36:57.000Z"}}