Metadata-Version: 2.4
Name: nemo-toolkit
Version: 3.0.0
Summary: NeMo - a toolkit for Conversational AI
Home-page: https://github.com/NVIDIA-NeMo/NeMo
Download-URL: https://github.com/NVIDIA-NeMo/NeMo/releases
Author: NVIDIA
Author-email: NVIDIA <nemo-toolkit@nvidia.com>
Maintainer: NVIDIA
Maintainer-email: NVIDIA <nemo-toolkit@nvidia.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
Project-URL: Download, https://github.com/NVIDIA-NeMo/NeMo/releases
Project-URL: Homepage, https://github.com/NVIDIA-NeMo/NeMo
Keywords: NLP,NeMo,deep,gpu,language,learning,learning,machine,nvidia,pytorch,speech,torch,tts
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Utilities
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aistore
Requires-Dist: fsspec>=2024.12.0
Requires-Dist: huggingface_hub>=0.24
Requires-Dist: numba; platform_system == "Darwin"
Requires-Dist: cuda-bindings; platform_system != "Darwin"
Requires-Dist: numpy>=1.22
Requires-Dist: onnx>=1.7.0
Requires-Dist: scikit-learn
Requires-Dist: setuptools>=70.0.0
Requires-Dist: smart-open
Requires-Dist: tensorboard
Requires-Dist: text-unidecode
Requires-Dist: torch>=2.6.0
Requires-Dist: tqdm>=4.41.0
Requires-Dist: wrapt
Provides-Extra: core
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "core"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "core"
Requires-Dist: omegaconf<=2.3; extra == "core"
Requires-Dist: torchmetrics>=0.11.0; extra == "core"
Requires-Dist: transformers; extra == "core"
Requires-Dist: wandb; extra == "core"
Requires-Dist: webdataset>=0.2.86; extra == "core"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "core"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "core"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "core"
Provides-Extra: lightning
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "lightning"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "lightning"
Requires-Dist: omegaconf<=2.3; extra == "lightning"
Requires-Dist: torchmetrics>=0.11.0; extra == "lightning"
Requires-Dist: transformers; extra == "lightning"
Requires-Dist: wandb; extra == "lightning"
Requires-Dist: webdataset>=0.2.86; extra == "lightning"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "lightning"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "lightning"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "lightning"
Provides-Extra: common-only
Requires-Dist: datasets>=3.2.0; extra == "common-only"
Requires-Dist: einops; extra == "common-only"
Requires-Dist: pandas; extra == "common-only"
Requires-Dist: sentencepiece<1.0.0; extra == "common-only"
Provides-Extra: asr-only
Requires-Dist: braceexpand; extra == "asr-only"
Requires-Dist: einops; extra == "asr-only"
Requires-Dist: kaldialign; extra == "asr-only"
Requires-Dist: lhotse>=1.33.0; extra == "asr-only"
Requires-Dist: librosa>=0.10.1; extra == "asr-only"
Requires-Dist: packaging; extra == "asr-only"
Requires-Dist: sacrebleu; extra == "asr-only"
Requires-Dist: scipy>=0.14; extra == "asr-only"
Requires-Dist: soundfile; extra == "asr-only"
Requires-Dist: whisper_normalizer; extra == "asr-only"
Provides-Extra: tts
Requires-Dist: einops; extra == "tts"
Requires-Dist: janome; extra == "tts"
Requires-Dist: jieba; extra == "tts"
Requires-Dist: librosa; extra == "tts"
Requires-Dist: matplotlib; extra == "tts"
Requires-Dist: nemo_text_processing; ("arm" not in platform_machine and "aarch" not in platform_machine and sys_platform != "darwin") and extra == "tts"
Requires-Dist: nltk; extra == "tts"
Requires-Dist: pandas; extra == "tts"
Requires-Dist: pypinyin; extra == "tts"
Requires-Dist: pypinyin-dict; extra == "tts"
Requires-Dist: pyopenjtalk; extra == "tts"
Requires-Dist: braceexpand; extra == "tts"
Requires-Dist: kaldialign; extra == "tts"
Requires-Dist: lhotse>=1.33.0; extra == "tts"
Requires-Dist: librosa>=0.10.1; extra == "tts"
Requires-Dist: packaging; extra == "tts"
Requires-Dist: sacrebleu; extra == "tts"
Requires-Dist: scipy>=0.14; extra == "tts"
Requires-Dist: soundfile; extra == "tts"
Requires-Dist: whisper_normalizer; extra == "tts"
Requires-Dist: datasets>=3.2.0; extra == "tts"
Requires-Dist: sentencepiece<1.0.0; extra == "tts"
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "tts"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "tts"
Requires-Dist: omegaconf<=2.3; extra == "tts"
Requires-Dist: torchmetrics>=0.11.0; extra == "tts"
Requires-Dist: transformers; extra == "tts"
Requires-Dist: wandb; extra == "tts"
Requires-Dist: webdataset>=0.2.86; extra == "tts"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "tts"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "tts"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "tts"
Provides-Extra: audio
Requires-Dist: einops; extra == "audio"
Requires-Dist: lhotse>=1.33.0; extra == "audio"
Requires-Dist: librosa>=0.10.0; extra == "audio"
Requires-Dist: matplotlib; extra == "audio"
Requires-Dist: pesq; (platform_machine != "x86_64" or platform_system != "Darwin") and extra == "audio"
Requires-Dist: pystoi; extra == "audio"
Requires-Dist: scipy>=0.14; extra == "audio"
Requires-Dist: soundfile; extra == "audio"
Requires-Dist: datasets>=3.2.0; extra == "audio"
Requires-Dist: pandas; extra == "audio"
Requires-Dist: sentencepiece<1.0.0; extra == "audio"
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "audio"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "audio"
Requires-Dist: omegaconf<=2.3; extra == "audio"
Requires-Dist: torchmetrics>=0.11.0; extra == "audio"
Requires-Dist: transformers; extra == "audio"
Requires-Dist: wandb; extra == "audio"
Requires-Dist: webdataset>=0.2.86; extra == "audio"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "audio"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "audio"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "audio"
Provides-Extra: speechlm2-only
Requires-Dist: nemo_automodel; extra == "speechlm2-only"
Requires-Dist: flashoptim; extra == "speechlm2-only"
Requires-Dist: peft<=0.18.0; extra == "speechlm2-only"
Provides-Extra: all
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "all"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "all"
Requires-Dist: omegaconf<=2.3; extra == "all"
Requires-Dist: torchmetrics>=0.11.0; extra == "all"
Requires-Dist: transformers; extra == "all"
Requires-Dist: wandb; extra == "all"
Requires-Dist: webdataset>=0.2.86; extra == "all"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "all"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "all"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "all"
Requires-Dist: datasets>=3.2.0; extra == "all"
Requires-Dist: einops; extra == "all"
Requires-Dist: pandas; extra == "all"
Requires-Dist: sentencepiece<1.0.0; extra == "all"
Requires-Dist: braceexpand; extra == "all"
Requires-Dist: kaldialign; extra == "all"
Requires-Dist: lhotse>=1.33.0; extra == "all"
Requires-Dist: librosa>=0.10.1; extra == "all"
Requires-Dist: packaging; extra == "all"
Requires-Dist: sacrebleu; extra == "all"
Requires-Dist: scipy>=0.14; extra == "all"
Requires-Dist: soundfile; extra == "all"
Requires-Dist: whisper_normalizer; extra == "all"
Requires-Dist: janome; extra == "all"
Requires-Dist: jieba; extra == "all"
Requires-Dist: librosa; extra == "all"
Requires-Dist: matplotlib; extra == "all"
Requires-Dist: nemo_text_processing; ("arm" not in platform_machine and "aarch" not in platform_machine and sys_platform != "darwin") and extra == "all"
Requires-Dist: nltk; extra == "all"
Requires-Dist: pypinyin; extra == "all"
Requires-Dist: pypinyin-dict; extra == "all"
Requires-Dist: pyopenjtalk; extra == "all"
Requires-Dist: librosa>=0.10.0; extra == "all"
Requires-Dist: pesq; (platform_machine != "x86_64" or platform_system != "Darwin") and extra == "all"
Requires-Dist: pystoi; extra == "all"
Requires-Dist: nemo_automodel; extra == "all"
Requires-Dist: flashoptim; extra == "all"
Requires-Dist: peft<=0.18.0; extra == "all"
Provides-Extra: cu12
Requires-Dist: torch==2.12.0+cu126; sys_platform == "linux" and extra == "cu12"
Requires-Dist: numba-cuda[cu12]; platform_system != "Darwin" and extra == "cu12"
Requires-Dist: cuda-python<13,>=12; platform_system != "Darwin" and extra == "cu12"
Provides-Extra: cu13
Requires-Dist: torch==2.12.0+cu132; sys_platform == "linux" and extra == "cu13"
Requires-Dist: numba-cuda[cu13]; platform_system != "Darwin" and extra == "cu13"
Requires-Dist: cuda-python<14,>=13; platform_system != "Darwin" and extra == "cu13"
Provides-Extra: compiled
Requires-Dist: onnx-ir==0.2.1; extra == "compiled"
Requires-Dist: onnxscript==0.7.0; extra == "compiled"
Requires-Dist: deep_ep==1.2.1; extra == "compiled"
Requires-Dist: nv-grouped-gemm==1.1.4.post8; extra == "compiled"
Requires-Dist: causal-conv1d==1.6.2.post1; extra == "compiled"
Requires-Dist: mamba-ssm==2.3.2.post1; extra == "compiled"
Requires-Dist: flash-attn==2.8.3; extra == "compiled"
Requires-Dist: transformer-engine[core_cu13,pytorch]==2.15; extra == "compiled"
Provides-Extra: compiled-a100
Requires-Dist: onnx-ir==0.2.1; extra == "compiled-a100"
Requires-Dist: onnxscript==0.7.0; extra == "compiled-a100"
Requires-Dist: nv-grouped-gemm==1.1.4.post8; extra == "compiled-a100"
Requires-Dist: causal-conv1d==1.6.2.post1; extra == "compiled-a100"
Requires-Dist: mamba-ssm==2.3.2.post1; extra == "compiled-a100"
Requires-Dist: flash-attn==2.8.3; extra == "compiled-a100"
Requires-Dist: transformer-engine[core_cu12,pytorch]==2.15; extra == "compiled-a100"
Provides-Extra: common
Requires-Dist: datasets>=3.2.0; extra == "common"
Requires-Dist: einops; extra == "common"
Requires-Dist: pandas; extra == "common"
Requires-Dist: sentencepiece<1.0.0; extra == "common"
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "common"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "common"
Requires-Dist: omegaconf<=2.3; extra == "common"
Requires-Dist: torchmetrics>=0.11.0; extra == "common"
Requires-Dist: transformers; extra == "common"
Requires-Dist: wandb; extra == "common"
Requires-Dist: webdataset>=0.2.86; extra == "common"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "common"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "common"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "common"
Provides-Extra: asr
Requires-Dist: braceexpand; extra == "asr"
Requires-Dist: einops; extra == "asr"
Requires-Dist: kaldialign; extra == "asr"
Requires-Dist: lhotse>=1.33.0; extra == "asr"
Requires-Dist: librosa>=0.10.1; extra == "asr"
Requires-Dist: packaging; extra == "asr"
Requires-Dist: sacrebleu; extra == "asr"
Requires-Dist: scipy>=0.14; extra == "asr"
Requires-Dist: soundfile; extra == "asr"
Requires-Dist: whisper_normalizer; extra == "asr"
Requires-Dist: datasets>=3.2.0; extra == "asr"
Requires-Dist: pandas; extra == "asr"
Requires-Dist: sentencepiece<1.0.0; extra == "asr"
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "asr"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "asr"
Requires-Dist: omegaconf<=2.3; extra == "asr"
Requires-Dist: torchmetrics>=0.11.0; extra == "asr"
Requires-Dist: transformers; extra == "asr"
Requires-Dist: wandb; extra == "asr"
Requires-Dist: webdataset>=0.2.86; extra == "asr"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "asr"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "asr"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "asr"
Provides-Extra: speechlm2
Requires-Dist: nemo_automodel; extra == "speechlm2"
Requires-Dist: flashoptim; extra == "speechlm2"
Requires-Dist: peft<=0.18.0; extra == "speechlm2"
Requires-Dist: braceexpand; extra == "speechlm2"
Requires-Dist: einops; extra == "speechlm2"
Requires-Dist: kaldialign; extra == "speechlm2"
Requires-Dist: lhotse>=1.33.0; extra == "speechlm2"
Requires-Dist: librosa>=0.10.1; extra == "speechlm2"
Requires-Dist: packaging; extra == "speechlm2"
Requires-Dist: sacrebleu; extra == "speechlm2"
Requires-Dist: scipy>=0.14; extra == "speechlm2"
Requires-Dist: soundfile; extra == "speechlm2"
Requires-Dist: whisper_normalizer; extra == "speechlm2"
Requires-Dist: datasets>=3.2.0; extra == "speechlm2"
Requires-Dist: pandas; extra == "speechlm2"
Requires-Dist: sentencepiece<1.0.0; extra == "speechlm2"
Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "speechlm2"
Requires-Dist: lightning<=2.4.0,>2.2.1; extra == "speechlm2"
Requires-Dist: omegaconf<=2.3; extra == "speechlm2"
Requires-Dist: torchmetrics>=0.11.0; extra == "speechlm2"
Requires-Dist: transformers; extra == "speechlm2"
Requires-Dist: wandb; extra == "speechlm2"
Requires-Dist: webdataset>=0.2.86; extra == "speechlm2"
Requires-Dist: nv_one_logger_core>=2.3.1; extra == "speechlm2"
Requires-Dist: nv_one_logger_training_telemetry>=2.3.1; extra == "speechlm2"
Requires-Dist: nv_one_logger_pytorch_lightning_integration>=2.3.1; extra == "speechlm2"
Requires-Dist: janome; extra == "speechlm2"
Requires-Dist: jieba; extra == "speechlm2"
Requires-Dist: librosa; extra == "speechlm2"
Requires-Dist: matplotlib; extra == "speechlm2"
Requires-Dist: nemo_text_processing; ("arm" not in platform_machine and "aarch" not in platform_machine and sys_platform != "darwin") and extra == "speechlm2"
Requires-Dist: nltk; extra == "speechlm2"
Requires-Dist: pypinyin; extra == "speechlm2"
Requires-Dist: pypinyin-dict; extra == "speechlm2"
Requires-Dist: pyopenjtalk; extra == "speechlm2"
Dynamic: author
Dynamic: download-url
Dynamic: home-page
Dynamic: license-file
Dynamic: maintainer
Dynamic: requires-python

[![Project Status: Active -- The project has reached a stable, usable state and is being actively developed.](http://www.repostatus.org/badges/latest/active.svg)](http://www.repostatus.org/#active)
[![Documentation](https://readthedocs.com/projects/nvidia-nemo/badge/?version=main)](https://docs.nvidia.com/nemo/speech/nightly/)
[![CodeQL](https://github.com/nvidia/nemo/actions/workflows/codeql.yml/badge.svg?branch=main&event=push)](https://github.com/nvidia/nemo/actions/workflows/codeql.yml)
[![NeMo core license and license for collections in this repo](https://img.shields.io/badge/License-Apache%202.0-brightgreen.svg)](https://github.com/NVIDIA/NeMo/blob/master/LICENSE)
[![Release version](https://badge.fury.io/py/nemo-toolkit.svg)](https://badge.fury.io/py/nemo-toolkit)
[![Python version](https://img.shields.io/pypi/pyversions/nemo-toolkit.svg)](https://badge.fury.io/py/nemo-toolkit)
[![PyPi total downloads](https://static.pepy.tech/personalized-badge/nemo-toolkit?period=total&units=international_system&left_color=grey&right_color=brightgreen&left_text=downloads)](https://pepy.tech/project/nemo-toolkit)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

# **NVIDIA NeMo Speech**
Checkout our [HuggingFace🤗 collection](https://huggingface.co/collections/nvidia/nemotron-speech) 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](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo?version=26.02).

- 2026-06: [Nemotron-3.5-ASR-Streaming-0.6B](https://huggingface.co/nvidia/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](https://huggingface.co/nvidia/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](https://build.nvidia.com/nvidia/nemotron-voicechat/modelcard) 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](https://build.nvidia.com/nvidia/nemotron-voicechat) and apply for [early access](https://developer.nvidia.com/nemotron-voicechat-early-access).
- 2026-03: [Nemotron-Speech-Streaming v2603](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) 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](https://huggingface.co/spaces/nvidia/nemotron-speech-streaming-en-0.6b) and check out
    [the NIM](https://build.nvidia.com/nvidia/nemotron-asr-streaming).
- 2026-03: [MagpieTTS v2602](https://huggingface.co/nvidia/magpie_tts_multilingual_357m) has been released with support
    for 9 languages(En, Es, De, Fr, Vi, It, Zh, Hi, Ja). Try out
    [the demo](https://huggingface.co/nvidia/magpie_tts_multilingual_357m) and check out
    [the NIM](https://build.nvidia.com/nvidia/magpie-tts-multilingual).
- 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](https://github.com/NVIDIA-NeMo/NeMo/releases/tag/v2.7.0)
- 2025-08: [Parakeet V3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) and
    [Canary V2](https://huggingface.co/nvidia/canary-1b-v2) have been released with speech recognition and translation
    support for 25 European languages.
- 2025-06: [Canary-Qwen-2.5B](https://huggingface.co/nvidia/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](https://docs.nvidia.com/nemo/speech/nightly/).

## 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](https://docs.pytorch.org/docs/stable/notes/serialization.html#torch-load-with-weights-only-true),
`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 Status](https://readthedocs.com/projects/nvidia-nemo/badge/?version=main)](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/)     | [Documentation of the latest (i.e. main) branch.](https://docs.nvidia.com/nemo/speech/nightly/)          |
| Stable  | [![Documentation Status](https://readthedocs.com/projects/nvidia-nemo/badge/?version=stable)](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/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](https://docs.astral.sh/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](#from-pypi-with-pip-fallback--bring-your-own-versions) below.

### From source with uv (recommended)

```bash
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](https://docs.nvidia.com/nemo/speech/nightly/) 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):

```bash
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`](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](https://pytorch.org/get-started/locally/)), then add NeMo and it **keeps your build**. `uv pip` (uv's fast, pip-compatible installer) works like `pip`:

```bash
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):

```bash
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](https://github.com/NVIDIA-NeMo/NeMo/blob/main/CONTRIBUTING.md) for the process.

## Licenses

NeMo is licensed under the [Apache License 2.0](https://github.com/NVIDIA/NeMo?tab=Apache-2.0-1-ov-file).
