{ "info": { "author": "Ivan Sorokin", "author_email": "sorokin.ivan@inbox.ru", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Science/Research", "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7", "Topic :: Scientific/Engineering", "Topic :: Scientific/Engineering :: Artificial Intelligence", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Python Modules" ], "description": "# PyTorch bindings for CUDA-Warp RNN-Transducer\n\n\n```python\ndef rnnt_loss(\n log_probs, # type: torch.FloatTensor\n labels, # type: torch.IntTensor\n frames_lengths, # type: torch.IntTensor\n labels_lengths, # type: torch.IntTensor\n average_frames=False, # type: bool\n reduction=None, # type: Optional[AnyStr]\n blank=0, # type: int\n):\n \"\"\"The CUDA-Warp RNN-Transducer loss.\n\n Args:\n log_probs (torch.Tensor): Input tensor (float) with shape\n (T, N, U, V) where T is the maximum number of input frames, N is the\n minibatch size, U is the maximum number of output labels and V is\n the vocabulary of labels (including the blank).\n labels (torch.IntTensor): Tensor with shape (N, U-1) representing the\n reference labels for all samples in the minibatch.\n frames_lengths (torch.IntTensor): Tensor with shape (N,) representing the\n number of frames for each sample in the minibatch.\n labels_lengths (torch.IntTensor): Tensor with shape (N,) representing the\n length of the transcription for each sample in the minibatch.\n average_frames (bool, optional): Specifies whether the loss of each\n sample should be divided by its number of frames. Default: ``False''.\n reduction (string, optional): Specifies the type of reduction.\n Default: None.\n blank (int, optional): label used to represent the blank symbol.\n Default: 0.\n \"\"\"\n # type: (...) -> torch.Tensor\n```\n\n## Requirements\n\n- C++11 compiler (tested with GCC 5.4).\n- Python: 3.5, 3.6, 3.7 (tested with version 3.6).\n- [PyTorch](http://pytorch.org/) >= 1.0.0 (tested with version 1.1.0).\n- [CUDA Toolkit](https://developer.nvidia.com/cuda-zone) (tested with version 10.0).\n\n\n\n## Install\n\nCurrently, there is no compiled version of the package. The following setup instructions compile the package from the source code locally.\n\n### From Pypi\n\n```bash\npip install warp_rnnt\n```\n\n### From GitHub\n\n```bash\ngit clone https://github.com/1ytic/warp-rnnt\ncd warp-rnnt/pytorch_binding\npython setup.py install\n```", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/1ytic/warp-rnnt/tree/master/pytorch_binding", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "warp-rnnt", "package_url": "https://pypi.org/project/warp-rnnt/", "platform": "", "project_url": "https://pypi.org/project/warp-rnnt/", "project_urls": { "Homepage": "https://github.com/1ytic/warp-rnnt/tree/master/pytorch_binding" }, "release_url": "https://pypi.org/project/warp-rnnt/0.1.0/", "requires_dist": null, "requires_python": "", "summary": "PyTorch bindings for CUDA-Warp RNN-Transducer", "version": "0.1.0" }, "last_serial": 5672372, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "7c1eb44d77d088070d126bd5fad2fcfe", "sha256": "8bf6e867f574f48a98e35d457ad7f84ce97561459ea029cdd68c9e9debf4f79b" }, "downloads": -1, "filename": "warp_rnnt-0.0.1.tar.gz", "has_sig": false, "md5_digest": "7c1eb44d77d088070d126bd5fad2fcfe", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4448, "upload_time": "2019-08-01T10:43:43", "url": "https://files.pythonhosted.org/packages/b6/fd/99ead04ab7dd362c2c1f3e6656a088f5bcbe14428bdd0866400a9a7bccd6/warp_rnnt-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "e33286e8418915878b1f03977bfa216a", "sha256": "221a5c8c9c0b2d44e9d88318de679857a0d81f72eb9faeae3b3cd6b4d028c8fa" }, "downloads": -1, "filename": "warp_rnnt-0.0.2.tar.gz", "has_sig": false, "md5_digest": "e33286e8418915878b1f03977bfa216a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7653, "upload_time": "2019-08-01T11:53:50", "url": "https://files.pythonhosted.org/packages/ff/50/5d60cf7c0cafdbfbe746659b11af33a4df4a83579b59892a552ee2a84d17/warp_rnnt-0.0.2.tar.gz" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "c4927af3bd741cce11eb2c8954dff4e7", "sha256": "c0397c8c98f6c32d3db9e168858faa7713af16479716467952439fdb9e9e992f" }, "downloads": -1, "filename": "warp_rnnt-0.0.3.tar.gz", "has_sig": false, "md5_digest": "c4927af3bd741cce11eb2c8954dff4e7", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 7661, "upload_time": "2019-08-01T11:58:03", "url": "https://files.pythonhosted.org/packages/05/66/11c33be22c80027b9fac0de593853054c82c1770bc60f4af009f02084915/warp_rnnt-0.0.3.tar.gz" } ], "0.0.4": [ { "comment_text": "", "digests": { "md5": "d367ce9b22e70b0c446cba34527ce710", "sha256": "21639b82c6307f265ed3f0b4ae25875f2c6c9689daefc8fe8fa2526a3f3933ea" }, "downloads": -1, "filename": "warp_rnnt-0.0.4.tar.gz", "has_sig": false, "md5_digest": "d367ce9b22e70b0c446cba34527ce710", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8528, "upload_time": "2019-08-01T12:19:25", "url": "https://files.pythonhosted.org/packages/a7/36/0c693a12fce42412b6ed13c597050c349f12f2eb837f94349c2133103965/warp_rnnt-0.0.4.tar.gz" } ], "0.0.5": [ { "comment_text": "", "digests": { "md5": "54ba57b6268bdbb9ae80c40deb8624b0", "sha256": "609fae269c89e175dec3c2738870ef14d0d2b385dd7eb5d67861646a32945cc0" }, "downloads": -1, "filename": "warp_rnnt-0.0.5.tar.gz", "has_sig": false, "md5_digest": "54ba57b6268bdbb9ae80c40deb8624b0", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8544, "upload_time": "2019-08-01T12:49:41", "url": "https://files.pythonhosted.org/packages/82/0f/492432812a341cdc9ba0a7352ef4c0187bdb5420094bf51694057bfbb76e/warp_rnnt-0.0.5.tar.gz" } ], "0.0.6": [ { "comment_text": "", "digests": { "md5": "4e0f20437ab5b5ad508d823e947c8113", "sha256": "13402439c83746ba931906383ffe10eafb9ff9a521fba1173e1c6de04d62162f" }, "downloads": -1, "filename": "warp_rnnt-0.0.6.tar.gz", "has_sig": false, "md5_digest": "4e0f20437ab5b5ad508d823e947c8113", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8773, "upload_time": "2019-08-07T14:26:02", "url": "https://files.pythonhosted.org/packages/f2/83/c5e92715b43947c894736c05abd5120549bcc2120644d40a91ebb0a9fb20/warp_rnnt-0.0.6.tar.gz" } ], "0.0.7": [ { "comment_text": "", "digests": { "md5": "0008822512458da4559c30072ab408b7", "sha256": "bafd62fd2ad7886013d9f17ddc143ee459ed4b1ed9701cdb15d85822b4a6adef" }, "downloads": -1, "filename": "warp_rnnt-0.0.7.tar.gz", "has_sig": false, "md5_digest": "0008822512458da4559c30072ab408b7", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8770, "upload_time": "2019-08-07T15:08:24", "url": "https://files.pythonhosted.org/packages/aa/8b/0736117e081da61948739a4d1b739967f79e64f6ed30ad6be5a811f11a09/warp_rnnt-0.0.7.tar.gz" } ], "0.0.8": [ { "comment_text": "", "digests": { "md5": "f7e3e59c91df3303de1e5f508adeba1a", "sha256": "17b3040cc38e6010a038e2d915873ddd973aebbfcfacba27e85a57a4714458c2" }, "downloads": -1, "filename": "warp_rnnt-0.0.8.tar.gz", "has_sig": false, "md5_digest": "f7e3e59c91df3303de1e5f508adeba1a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8776, "upload_time": "2019-08-07T15:32:52", "url": "https://files.pythonhosted.org/packages/c8/52/37e04fe44633a1f2335b5e5427e51b56deed15d871b4a2a644c7c3cc30d9/warp_rnnt-0.0.8.tar.gz" } ], "0.0.9": [ { "comment_text": "", "digests": { "md5": "383b315d6b200d302921e97d2b748712", "sha256": "bed1d691dc054a181903d45ce64eb6229cf83758926cbf77d4365a8cfa86155b" }, "downloads": -1, "filename": "warp_rnnt-0.0.9.tar.gz", "has_sig": false, "md5_digest": "383b315d6b200d302921e97d2b748712", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8778, "upload_time": "2019-08-07T15:50:11", "url": "https://files.pythonhosted.org/packages/5f/3a/48a83fe0f353c5177a3b59c4b370978e39e4a440e1962ba1bed0a728770b/warp_rnnt-0.0.9.tar.gz" } ], "0.1.0": [ { "comment_text": "", "digests": { "md5": "a2a057e72e43e8aec492fa8242f1b839", "sha256": "e3637a89fcefdbf5a456867bd568cab67d6c911167a756af304eb0877c329b82" }, "downloads": -1, "filename": "warp_rnnt-0.1.0.tar.gz", "has_sig": false, "md5_digest": "a2a057e72e43e8aec492fa8242f1b839", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8768, "upload_time": "2019-08-13T15:11:02", "url": "https://files.pythonhosted.org/packages/86/6d/1389db3abbeaaed0279516878275b7c8f536c70323376bfd46a6e95e4040/warp_rnnt-0.1.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "a2a057e72e43e8aec492fa8242f1b839", "sha256": "e3637a89fcefdbf5a456867bd568cab67d6c911167a756af304eb0877c329b82" }, "downloads": -1, "filename": "warp_rnnt-0.1.0.tar.gz", "has_sig": false, "md5_digest": "a2a057e72e43e8aec492fa8242f1b839", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8768, "upload_time": "2019-08-13T15:11:02", "url": "https://files.pythonhosted.org/packages/86/6d/1389db3abbeaaed0279516878275b7c8f536c70323376bfd46a6e95e4040/warp_rnnt-0.1.0.tar.gz" } ] }