Meta tags:
description=A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) - NVIDIA-NeMo/Speech;

Headings (most frequently used words):

uh, oh, nemo, speech, navigation, saved, searches, nvidia, to, your, files, footer, from, with, search, code, repositories, users, issues, pull, requests, provide, feedback, menu, use, filter, results, more, quickly, folders, and, latest, commit, history, repository, updates, introduction, requirements, developer, documentation, install, contribute, licenses, about, releases, 86, packages, contributors, languages, source, uv, recommended, docker, turnkey, our, supported, stack, pypi, pip, fallback, bring, own, versions, topics, resources, license, contributing, security, policy, stars, watchers, forks,

Text of the page (most frequently used words):
the (48), and (40), #speech (35), nemo (34), for (28), with (22), cuda (21), your (17), pytorch (16), security (15), github (15), pip (14), code (13), all (12), 2026 (11), you (10), this (10), python (10), nvidia (10), install (9), build (9), see (9), from (9), support (9), released (9), please (8), reload (8), asr (8), use (8), docker (8), was (7), tts (7), built (7), extra (7), our (7), source (7), documentation (7), has (7), been (7), view (7), docs (6), loading (6), latest (6), contributing (6), license (6), index (6), stack (6), a100 (6), container (6), more (6), nemotron (6), out (6), pylintrc (6), flake8 (6), enterprise (6), can (5), community (5), navigation (5), other (5), there (5), error (5), while (5), page (5), recognition (5), pull (5), add (5), lock (5), recommended (5), files (5), open (5), latency (5), commit (5), search (5), that (4), not (4), languages (4), readme (4), developers (4), models (4), https (4), toolkit (4), cu13 (4), supported (4), baseline (4), versions (4), default (4), dockerfile (4), git (4), tools (4), streaming (4), yml (4), claude (4), actions (4), issues (4), repository (3), stars (3), apache (3), resources (3), generative (3), translation (3), topics (3), com (3), framework (3), researchers (3), working (3), language (3), multimodal (3), automatic (3), text (3), url (3), cu12 (3), config (3), own (3), sync (3), locked (3), any (3), version (3), works (3), gpu_target (3), run (3), compiled (3), installs (3), test (3), are (3), one (3), existing (3), stable (3), release (3), developer (3), model (3), checkpoints (3), have (3), they (3), setup (3), pre (3), last (3), try (3), demo (3), quality (3), agents (3), external (3), name (3), insights (3), requests (3), signed (3), settings (3), another (3), tab (3), window (3), refresh (3), session (3), sign (3), saved (3), feedback (3), grade (3), features (3), copilot (3), platform (3), solutions (3), explore (3), manage (2), status (2), footer (2), releases (2), neural (2), forks (2), policy (2), speaker (2), scalable (2), large (2), download (2), org (2), whl (2), pinned (2), read (2), required (2), bring (2), here (2), first (2), cpu (2), etc (2), fallback (2), set (2), base (2), image (2), clone (2), h100 (2), ngc (2), turnkey (2), automodel (2), better (2), full (2), guide (2), without (2), via (2), activate (2), venv (2), group (2), actively (2), below (2), main (2), using (2), case (2), before (2), only (2), torch (2), load (2), weights_only (2), options (2), inference (2), above (2), create (2), new (2), trained (2), 2025 (2), wer (2), english (2), canary (2), parakeet (2), repo (2), focus (2), llm (2), magpietts (2), users (2), check (2), nim (2), early (2), access (2), voicechat (2), pyproject (2), toml (2), nemo_dependencies (2), codecov (2), manifest (2), citation (2), cff (2), secrets (2), readthedocs (2), yaml (2), gitignore (2), dockerignore (2), coveragerc (2), tutorials (2), tests (2), scripts (2), examples (2), cursor (2), codex (2), 436 (2), commits (2), message (2), menu (2), projects (2), discussions (2), appearance (2), cancel (2), available (2), searches (2), repositories (2), business (2), advanced (2), customer (2), services (2), devops (2), app (2), perform, action, time, share, personal, information, cookies, contact, privacy, terms, inc, shell, jupyter, notebook, contributors, packages, apr, modules, report, watching, 231, watchers, custom, properties, activity, diariazation, deeplearning, networks, synthesis, machine, nightly, html, about, licensed, under, licenses, welcome, contributions, refer, process, contribute, cu132, cu126, instead, matching, wheel, project, applies, replaces, reserve, reproducing, plain, prefer, target, then, fast, compatible, installer, like, keeps, matrix, pypi, convenience, header, arguments, base_image, both, buildx, gpus, bash, workspace, pwd, coming, soon, command, prebuilt, will, published, backend, runs, dependencies, benefit, dedicated, accelerated, backends, transformer, engine, flashattention, mamba, grouped, gemm, moe, deepep, performance, these, kernels, come, hopper, blackwell, extras, list, details, installation, h100plus, optionally, speechlm2, into, editable, suite, linux, mutually, exclusive, pass, exactly, path, exact, bin, cmd, way, which, reproduces, tested, committed, need, different, also, over, environment, most, recent, added, branch, description, defaults, some, may, require, env, var, running, uses, however, should, done, trusted, untrusted, sources, than, weights, risk, arbitrary, execution, torch_force_no_weights_only_load, false, true, already, satisfies, those, minimums, top, kept, shipped, official, simply, combination, make, reproducible, but, hard, requirement, replacing, gpu, training, choice, choosing, requirements, technical, user, including, llms, designed, help, efficiently, customize, deploy, leveraging, introduction, record, setting, leaderboard, qwen, european, pivoted, audio, modalities, checkpoint, enables, pick, their, optimal, point, accuracy, pareto, curve, v2602, updated, larger, diverse, corpus, resulting, lower, across, modes, v2603, now, nano, backbone, decoder, delivers, duplex, natural, interruptible, conversations, low, apply, high, offline, minimum, 160ms, punctuation, capitalization, unified, controllable, 80ms, 240, 2400, 1xh100, concurrent, streams, cache, aware, fastconformer, architecture, after, split, scheduled, june, undergoes, transformation, updates, checkout, weight, demos, huggingface, collection, items, history, date, folders, file, tags, branches, additional, 118, star, fork, must, change, notification, notifications, public, dismiss, alert, switched, accounts, resetting, qualifiers, query, filter, results, quickly, submit, include, email, address, contacted, every, piece, take, input, very, seriously, provide, syntax, tips, clear, jump, pricing, premium, ons, powered, collections, trending, archive, program, accelerator, maintainer, lab, programs, fund, sponsors, partners, trust, center, forum, skills, ebooks, reports, events, webinars, stories, type, software, development, topic, industries, government, manufacturing, financial, healthcare, industry, cases, devsecops, modernization, nonprofits, startups, small, medium, teams, enterprises, company, size, marketplace, changelog, blog, why, stop, leaks, start, secret, protection, secure, find, fix, vulnerabilities, application, changes, review, plan, track, work, instant, dev, environments, codespaces, automate, workflow, workflows, integrate, mcp, registry, direct, issue, merge, write, creation, toggle, skip, content,

Text of the page (random words):
github nvidia nemo speech a scalable generative ai framework built for researchers and developers working on large language models multimodal and speech ai automatic speech recognition and text to speech github skip to content navigation menu toggle navigation sign in appearance settings platform ai code creation github copilot write better code with ai github copilot app direct agents from issue to merge mcp registry new integrate external tools developer workflows actions automate any workflow codespaces instant dev environments issues plan and track work code review manage code changes application security github advanced security find and fix vulnerabilities code security secure your code as you build secret protection stop leaks before they start explore why github documentation blog changelog marketplace view all features solutions by company size enterprises small and medium teams startups nonprofits by use case app modernization devsecops devops ci cd view all use cases by industry healthcare financial services manufacturing government view all industries view all solutions resources explore by topic ai software development devops security view all topics explore by type customer stories events webinars ebooks reports business insights github skills support services documentation customer support community forum trust center partners view all resources open source community github sponsors fund open source developers programs security lab maintainer community accelerator github stars archive program repositories topics trending collections enterprise enterprise solutions enterprise platform ai powered developer platform available add ons github advanced security enterprise grade security features copilot for business enterprise grade ai features premium support enterprise grade 24 7 support pricing search or jump to search code repositories users issues pull requests search clear search syntax tips provide feedback we read every piece of feedback and take your input very seriously include my email address so i can be contacted cancel submit feedback saved searches use saved searches to filter your results more quickly name query to see all available qualifiers see our documentation cancel create saved search sign in sign up appearance settings resetting focus you signed in with another tab or window reload to refresh your session you signed out in another tab or window reload to refresh your session you switched accounts on another tab or window reload to refresh your session dismiss alert message uh oh there was an error while loading please reload this page nvidia nemo speech public notifications you must be signed in to change notification settings fork 3 5k star 17 8k code issues 92 pull requests 118 discussions actions projects security and quality 2 insights additional navigation options code issues pull requests discussions actions projects security and quality insights nvidia nemo speech main branches tags go to file code open more actions menu folders and files name name last commit message last commit date latest commit history 9 436 commits 9 436 commits claude claude codex codex cursor cursor github github docker docker docs docs examples examples external external nemo nemo scripts scripts tests tests tools tools tutorials tutorials coveragerc coveragerc dockerignore dockerignore flake8 flake8 flake8 other flake8 other flake8 speech flake8 speech gitignore gitignore pre commit config yaml pre commit config yaml pylintrc pylintrc pylintrc other pylintrc other pylintrc speech pylintrc speech readthedocs yml readthedocs yml secrets baseline secrets baseline agents md agents md citation cff citation cff claude md claude md contributing md contributing md license license manifest in manifest in readme md readme md security md security md codecov yml codecov yml nemo_dependencies py nemo_dependencies py pyproject toml pyproject toml setup py setup py uv lock uv lock view all files repository files navigation readme contributing apache 2 0 license security more items nvidia nemo speech checkout our huggingface collection for the latest open weight checkpoints and demos updates the first release of nemo speech after nemo repository split is scheduled for june 2026 as the repo undergoes transformation for the latest stable released version please use the 26 02 ngc container 2026 06 nemotron 3 5 asr streaming 0 6b has been released with 40 languages supported controllable latency 80ms 1s and 240 2400 1xh100 concurrent streams built on cache aware fastconformer architecture 2026 04 parakeet unified en 0 6b has been released with high quality offline and streaming with a minimum latency of 160ms inference in one model for english language with punctuation and capitalization support 2026 03 nemotron 3 voicechat is now released in early access built on the nemotron nano v2 llm backbone with nemotron speech and tts decoder voicechat delivers full duplex natural interruptible conversations with low latency try out the demo and apply for early access 2026 03 nemotron speech streaming v2603 has been updated it has been trained on a larger and more diverse corpus resulting in lower wer across all latency modes try out the demo and check out the nim 2026 03 magpietts v2602 has been released with support for 9 languages en es de fr vi it zh hi ja try out the demo and check out the nim 2026 01 nemotron speech streaming was released one checkpoint that enables users to pick their optimal point on the latency accuracy pareto curve 2026 01 magpietts was released 2026 this repo has pivoted to focus on audio speech and multimodal llm for the last nemo release with support for more modalities see v2 7 0 2025 08 parakeet v3 and canary v2 have been released with speech recognition and translation support for 25 european languages 2025 06 canary qwen 2 5b has been released with record setting 5 63 wer on english open asr leaderboard introduction nvidia nemo speech is built for researchers and pytorch developers working on speech models including automatic speech recognition asr text to speech tts and speech llms it is designed to help you efficiently create customize and deploy new ai models by leveraging existing code and pre trained model checkpoints for technical documentation please see the nemo framework user guide requirements nemo speech works with the python pytorch and cuda versions of your choosing python 3 12 or above pytorch 2 7 or above cpu cuda etc your choice nvidia gpu cuda required for training recommended for inference if you already have a python pytorch cuda stack that satisfies those minimums nemo speech installs on top of it without replacing it so your existing pytorch build is kept see the install options below the versions pinned in uv lock and shipped in the official container python 3 13 pytorch 2 12 cuda 12 6 13 2 are simply the combination we actively test and support they make setup turnkey and reproducible but they are not a hard requirement as of pytorch 2 6 torch load defaults to using weights_only true some model checkpoints may require using weights_only false in this case you can set the env var torch_force_no_weights_only_load 1 before running code that uses torch load however this should only be done with trusted files loading files from untrusted sources with more than weights only can have the risk of arbitrary code execution developer documentation version status description latest documentation of the latest i e main branch stable documentation of the stable i e most recent release to be added install nemo speech the recommended way to install nemo speech is from source with uv which reproduces our actively tested stack from the committed uv lock if you need different python pytorch cuda versions nemo also installs over your existing environment via pip see the pip fallback below from source with uv recommended git clone https github com nvidia nemo nemo git cd nemo uv sync extra all extra cu13 cuda 13 x recommended use extra cu12 for cuda 12 x this installs our supported stack python 3 13 pytorch 2 12 cuda 13 2 into venv with nemo editable add group test for the test suite or group docs to build the docs run tools via uv run cmd or activate with source venv bin activate on linux cu12 and cu13 are mutually exclusive pass exactly one cu13 is the default for the exact container baseline add locked python 3 13 the path the dockerfile and ci use speechlm2 automodel the automodel backend runs without any compiled dependencies it can optionally benefit from dedicated accelerated backends transformer engine flashattention mamba grouped gemm moe deepep for better performance these source built kernels come from the compiled hopper blackwell or compiled a100 a100 extras built by docker dockerfile gpu_target h100plus a100 see the installation guide for the full list and build details docker turnkey our supported stack ngc container coming soon the pull command for the prebuilt nemo speech container image will be published here to build the container from source cuda 13 h100 by default git clone https github com nvidia nemo nemo git cd nemo docker buildx build f docker dockerfile t nemo speech cuda 13 h100 default docker run rm it gpus all v pwd workspace nemo speech bash for a100 set gpu_target a100 a100 works with both cuda 12 and cuda 13 cuda 13 the default base image is recommended the cuda 12 base is a convenience see the header of docker dockerfile for all build arguments base_image gpu_target from pypi with pip fallback bring your own versions prefer your own python pytorch cuda install your pytorch first any version 2 7 for your cpu cuda etc target see the pytorch install matrix then add nemo and it keeps your build uv pip uv s fast pip compatible installer works like pip uv pip install nemo toolkit asr tts or plain pip install nemo toolkit asr tts ️ do not use uv sync locked for a bring your own stack it applies uv lock and replaces your python pytorch cuda with the supported baseline use uv pip pip here reserve uv sync locked for reproducing our stack to instead pull our pinned pytorch build add the cuda extra and the matching wheel index pip uv pip do not read uv s project index config so extra index url is required pip install nemo toolkit asr tts cu13 extra index url https download pytorch org whl cu132 cuda 13 x pip install nemo toolkit asr tts cu12 extra index url https download pytorch org whl cu126 cuda 12 x contribute to nemo we welcome community contributions please refer to contributing md for the process licenses nemo is licensed under the apache license 2 0 about a scalable generative ai framework built for researchers and developers working on large language models multimodal and speech ai automatic speech recognition and text to speech docs nvidia com nemo speech nightly index html topics machine translation tts speech synthesis neural networks deeplearning speaker recognition asr speech translation speaker diariazation generative ai resources readme license apache 2 0 license contributing contributing security policy security policy uh oh there was an error while loading please reload this page activity custom properties stars 17 8k stars watchers 231 watching forks 3 5k forks report repository releases 86 nvidia neural modules 2 7 3 latest apr 23 2026 85 releases packages 0 uh oh there was an error while loading please reload this page uh oh there was an error while loading please reload this page contributors uh oh there was an error while loading please reload this page languages python 73 9 jupyter notebook 24 9 shell 1 1 other 0 1 footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal information you can t perform that action at this time