pyannote-audio-legacy/tutorials/applying_a_model.ipynb

{"cells":[{"cell_type":"markdown","metadata":{"id":"rkz0m90MTNdU"},"source":["**<a href=\"https://colab.research.google.com/github/pyannote/pyannote-audio/blob/develop/tutorials/applying_a_model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>**"]},{"cell_type":"markdown","metadata":{"id":"vDBFFNeGWF0v"},"source":["# Applying a pretrained model\n","\n","In this tutorial, you will learn how to apply `pyannote.audio` models on an audio file, whose manual annotation is depicted below"]},{"cell_type":"markdown","metadata":{"id":"DcXUj3lVTkWz"},"source":["## Tutorial setup"]},{"cell_type":"code","execution_count":3,"metadata":{"executionInfo":{"elapsed":221,"status":"ok","timestamp":1704806538788,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"p7uwJtF1W0Od"},"outputs":[],"source":["# preparing notebook for visualization purposes\n","# (only show outputs between t=0s and t=30s)\n","from pyannote.core import notebook, Segment\n","notebook.crop = Segment(0, 30)"]},{"cell_type":"markdown","metadata":{"id":"yr4ONuV9Tlgj"},"source":["### `Google Colab` setup"]},{"cell_type":"markdown","metadata":{"id":"OaXXRLf5Tp2D"},"source":["If you are running this tutorial on `Colab`, execute the following commands in order to setup `Colab` environment. These commands will install `pyannote.audio`, and download resources used in this tutorial."]},{"cell_type":"code","execution_count":null,"metadata":{"id":"wQub0z0VTzpU"},"outputs":[],"source":["!pip install -qq pyannote.audio==3.1.1\n","!pip install -qq ipython==7.34.0\n","!wget -q \"https://github.com/pyannote/pyannote-audio/raw/develop/tutorials/assets/sample.wav\"\n","!wget -q \"https://github.com/pyannote/pyannote-audio/raw/develop/tutorials/assets/sample.rttm\"\n","!wget -q -P ./assets/ \"https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/assets/download-model.png\""]},{"cell_type":"markdown","metadata":{"id":"4Qy1iMvGVaHF"},"source":["⚠ Restart the runtime (Runtime > Restart session)."]},{"cell_type":"code","execution_count":18,"metadata":{"executionInfo":{"elapsed":203,"status":"ok","timestamp":1704807063824,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"vHwJOO-sUdF2"},"outputs":[],"source":["AUDIO_FILE = \"sample.wav\"\n","REFERENCE = \"sample.rttm\""]},{"cell_type":"markdown","metadata":{"id":"CUmGkiY-V-wI"},"source":["### Non `Google Colab` setup"]},{"cell_type":"markdown","metadata":{"id":"_E4buYUQWXE5"},"source":["If you are not using Colab, clone `pyannote.audio` [GitHub repository](https://github.com/pyannote/pyannote-audio) and update ROOT_DIR accordingly"]},{"cell_type":"code","execution_count":2,"metadata":{"executionInfo":{"elapsed":232,"status":"ok","timestamp":1704806051725,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"Wii7pyvSTIa1"},"outputs":[],"source":["# clone pyannote-audio Github repository and update ROOT_DIR accordingly\n","ROOT_DIR = \"<path-to-pyannote-github-repo>/pyannote-audio\"\n","AUDIO_FILE = f\"{ROOT_DIR}/tutorials/assets/sample.wav\"\n","REFERENCE = f\"{ROOT_DIR}/tutorials/assets/sample.rttm\""]},{"cell_type":"markdown","metadata":{"id":"o01jf1VTXC8u"},"source":["## References\n","\n","First, let's take a look at the audio reference used in this tutorial. It can be accessed as follows:"]},{"cell_type":"code","execution_count":4,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":259},"executionInfo":{"elapsed":542,"status":"ok","timestamp":1704807074571,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"Q4hYAMEiTIa3","outputId":"9fecf73e-2448-4a4e-93e4-f35d2ec4da8b"},"outputs":[{"data":{"image/png":"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","text/plain":["<pyannote.core.annotation.Annotation at 0x7fd98f1c3550>"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["from pyannote.database.util import load_rttm\n","\n","reference = load_rttm(REFERENCE)[\"sample\"]\n","reference"]},{"cell_type":"markdown","metadata":{"id":"3cpR2brxTIa6"},"source":["## Loading models from 🤗 hub\n","\n","A bunch of pretrained models are available on [🤗 Huggingface model hub](https://hf.co/models?other=pyannote-audio-model) and can be listed by looking for the [`pyannote-audio-model`](https://hf.co/models?other=pyannote-audio-model) tag."]},{"cell_type":"code","execution_count":5,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":1201,"status":"ok","timestamp":1704807077972,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"OXNju-sFTIa7","outputId":"6c587fd6-f14f-4162-81ba-0609153aa7f2"},"outputs":[{"data":{"text/plain":["['pyannote/TestModelForContinuousIntegration',\n"," 'pyannote/embedding',\n"," 'pyannote/segmentation',\n"," 'pyannote/brouhaha',\n"," 'pyannote/segmentation-3.0',\n"," 'pyannote/wespeaker-voxceleb-resnet34-LM']"]},"execution_count":5,"metadata":{},"output_type":"execute_result"}],"source":["from huggingface_hub import HfApi\n","available_models = [m.modelId for m in HfApi().list_models(filter=\"pyannote-audio-model\")]\n","list(filter(lambda p: p.startswith(\"pyannote/\"), available_models))"]},{"cell_type":"markdown","metadata":{"id":"LrQ2ykU4TIa-"},"source":["Official [pyannote.audio](https://github.com/pyannote/pyannote-audio) models (i.e. those under the [`pyannote` organization](https://hf.co/pyannote) umbrella) are open-source, but gated. It means that you have to first accept users conditions on their respective Huggingface page to access the pretrained weights and hyper-parameters. Despite this initial process, those models can perfectly be downloaded for later offline use: keep reading this tutorial until the end to learn how to do that.\n","\n","For instance, to load the speaker segmentation model used in this tutorial, you have to visit [hf.co/pyannote/segmentation](https://hf.co/pyannote/segmentation), accept the terms, and log in using `notebook_login` below:"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":145,"referenced_widgets":["a73cecb8608f491e8f996c5114df4d0f","bc10c6804346449b8e349728a1acb8d2","73915caf6d1042ca9a27853986217ae2","2d1965df902b4b7eb6e4e28e44d6e32b","b2e03b10050d46548932f429bcc18d81","0c537fef94bd4a3d8c42d981a70ea35b","79d55946b3764666a0b57a72722f6c19","988c83c85f7d44d0be949de6eedcf977","53919e13e42441d9b8cf5eb4f2effe96","47da80658de14604a7cc5268b951c172","c7fbfffbbc304f0ba025e03beb8f638a","416ffb7703b1404ab1c19c6b1ecafb4c","5be7421c575d41128d0675dc9abbc196","8b3353af24074ce5b5d2d9b162c61062","cd40e31c191044b7a0f8fa4694ad6380","ecbb880cf0044404ab9bfc5995656807","79287ffea49a4e4a80191b1157de15cc","0e04a45510f346b8ab3c465b10ccdfd2","bf5c88fe90f0462b95aa8a81467c1e9d","09ee64808a5c431b928066a4cb287a78","52a4a1aab39741f2a0499428f07a4c25","f23cc133109c4ecb9b383f118bcc71aa","2b91f4b11d5848c0b6795b649bc2d7bc","b437981acb894f97ad45daaebe2734c7","01a79756e1104be0bcbe1d233677d605","990375a830eb4cd79c69ad78b9ac685b","49cb317b141a43b7b8ce342e2d62ab03","abc23089f4ef4d2a9f8a104fb1dba14a","57cf64e9c70e4057a76c2f3fb1e9b191","5e90e4818f1f43f2aa4714e0e40dc15d","fb027db34fd740c2a4758d650ae3f73c","1a30ac8b519948bbad72886049b53d55"]},"executionInfo":{"elapsed":215,"status":"ok","timestamp":1704807086866,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"x9iQwHjfTIa_","outputId":"b5b3c597-4c2e-4306-e6a5-9ccc9ed19d08"},"outputs":[],"source":["from huggingface_hub import notebook_login\n","notebook_login()"]},{"cell_type":"markdown","metadata":{"id":"fUvB3kwwTIbA"},"source":["Once authenticated, you can load the model..."]},{"cell_type":"code","execution_count":null,"metadata":{"executionInfo":{"elapsed":3254,"status":"ok","timestamp":1704807117456,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"IzYUeS99TIbE"},"outputs":[],"source":["from pyannote.audio import Model\n","model = Model.from_pretrained(\"pyannote/segmentation-3.0\", use_auth_token=True)"]},{"cell_type":"markdown","metadata":{"id":"UxuGtfPoTIbF"},"source":["... which consists in SincNet feature extraction (`sincnet`) , LSTM sequence modeling (`lstm`), a few feed-forward layers (`linear`), and a final multi-label `classifier`:"]},{"cell_type":"code","execution_count":8,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":223,"status":"ok","timestamp":1704807124564,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"BQ2RDdqUTIbH","outputId":"6caf82ff-7a19-401d-ad79-8350315ec9de"},"outputs":[{"data":{"text/plain":["  | Name       | Type       | Params | In sizes       | Out sizes                                  \n","---------------------------------------------------------------------------------------------------------\n","0 | sincnet    | SincNet    | 42.6 K | [1, 1, 160000] | [1, 60, 589]                               \n","1 | lstm       | LSTM       | 1.4 M  | [1, 589, 60]   | [[1, 589, 256], [[8, 1, 128], [8, 1, 128]]]\n","2 | linear     | ModuleList | 49.4 K | ?              | ?                                          \n","3 | classifier | Linear     | 903    | [1, 589, 128]  | [1, 589, 7]                                \n","4 | activation | LogSoftmax | 0      | [1, 589, 7]    | [1, 589, 7]                                \n","---------------------------------------------------------------------------------------------------------\n","1.5 M     Trainable params\n","0         Non-trainable params\n","1.5 M     Total params\n","5.893     Total estimated model params size (MB)"]},"execution_count":8,"metadata":{},"output_type":"execute_result"}],"source":["from pytorch_lightning.utilities.model_summary import summarize\n","\n","summarize(model)"]},{"cell_type":"markdown","metadata":{"id":"ahfL4saFTIbI"},"source":["More details about the model are provided by its specifications..."]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":195,"status":"ok","timestamp":1704807127275,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"B0OFti5ITIbJ","outputId":"c2d74d99-7727-4f36-9a0f-4ec2aa76bd25"},"outputs":[{"data":{"text/plain":["Specifications(problem=<Problem.MONO_LABEL_CLASSIFICATION: 1>, resolution=<Resolution.FRAME: 1>, duration=10.0, min_duration=None, warm_up=(0.0, 0.0), classes=['speaker#1', 'speaker#2', 'speaker#3'], powerset_max_classes=2, permutation_invariant=True)"]},"execution_count":9,"metadata":{},"output_type":"execute_result"}],"source":["specs = model.specifications\n","specs"]},{"cell_type":"markdown","metadata":{"id":"kP5sRrrdTIbK"},"source":["... which can be understood like that:\n","\n","* `duration = 10.0`: the model ingests 10s-long audio chunks\n","* `Resolution.FRAME`:  the model output a sequence of frame-wise scores\n","* `len(classes) = 3`: model handle chunks with up to 3 speakers\n","* `powerset_max_classes = 2`: at most 2 speakers can talk at the same time (overlapped speech)\n","The previous two specifications give the classes that the model can predict: {no speech}, {spk1}, {spk2}, {spk3}, {spk1, spk2}, {spk1, spk3}, {spk2, spk3}, so a total of 7 classes.\n","More details about powerset can be found in the article `A. Plaquet and H. Bredin, “Powerset multi-class cross entropy loss for neural speaker diarization,” 2023.`, available [here](https://arxiv.org/abs/2310.13025).\n","* `Problem.MONO_LABEL_CLASSIFICATION`: the model prediction associates one class to each time frame"]},{"cell_type":"markdown","metadata":{"id":"wTY4-nT2TIbM"},"source":["To apply the model on the audio file, we wrap it into an `Inference` instance:"]},{"cell_type":"code","execution_count":10,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":657},"executionInfo":{"elapsed":1614,"status":"ok","timestamp":1704807131091,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"vKcaevu8TIbN","outputId":"e020fdb9-3c92-4f76-fcec-5053c1842d19"},"outputs":[{"data":{"image/png":"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","text/plain":["<pyannote.core.feature.SlidingWindowFeature at 0x7fd88f237fd0>"]},"execution_count":10,"metadata":{},"output_type":"execute_result"}],"source":["from pyannote.audio import Inference\n","inference = Inference(model, step=2.5)\n","output = inference(AUDIO_FILE)\n","output"]},{"cell_type":"markdown","metadata":{"id":"MoqfhoX_TIbO"},"source":["For each of the 9 positions of the 10s window, the model outputs a 3-dimensional vector every 17ms (589 frames for 10 seconds), corresponding to the probabilities that each of (up to) 3 speakers is active.   "]},{"cell_type":"code","execution_count":11,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":196,"status":"ok","timestamp":1704807141814,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"JObvduJMTIbO","outputId":"af45591c-c30d-401a-8906-db029140cea2"},"outputs":[{"data":{"text/plain":["(9, 589, 3)"]},"execution_count":11,"metadata":{},"output_type":"execute_result"}],"source":["output.data.shape"]},{"cell_type":"markdown","metadata":{"id":"Zdk-iqOaTIbQ"},"source":["## Processing a file from memory\n","\n","In case the audio file is not stored on disk, pipelines can also process audio provided as a `{\"waveform\": ..., \"sample_rate\": ...}` dictionary."]},{"cell_type":"code","execution_count":12,"metadata":{"executionInfo":{"elapsed":229,"status":"ok","timestamp":1704807145587,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"oFQrkl01TIbQ"},"outputs":[{"name":"stdout","output_type":"stream","text":["type(waveform)=<class 'torch.Tensor'>\n","waveform.shape=torch.Size([1, 480000])\n","waveform.dtype=torch.float32\n"]}],"source":["import torchaudio\n","waveform, sample_rate = torchaudio.load(AUDIO_FILE)\n","\n","print(f\"{type(waveform)=}\")\n","print(f\"{waveform.shape=}\")\n","print(f\"{waveform.dtype=}\")\n","\n","audio_in_memory = {\"waveform\": waveform, \"sample_rate\": sample_rate}"]},{"cell_type":"code","execution_count":13,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":657},"executionInfo":{"elapsed":1904,"status":"ok","timestamp":1704807149946,"user":{"displayName":"Clément PAGES","userId":"11757386314069785178"},"user_tz":-60},"id":"j2zi1CzHTIbR","outputId":"fb8ac3d0-c9f0-4b0a-c01f-a10612bdf254"},"outputs":[{"data":{"image/png":"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","text/plain":["<pyannote.core.feature.SlidingWindowFeature at 0x7fd98e96a590>"]},"execution_count":13,"metadata":{},"output_type":"execute_result"}],"source":["output = inference(audio_in_memory)\n","output"]},{"cell_type":"markdown","metadata":{"id":"aB5QNx7lTIbS"},"source":["## Processing part of a file\n","\n","If needed, `Inference` can be used to process only part of a file:"]},{"cell_type":"code","execution_count":19,"metadata":{"id":"E0Pydt0VTIbT"},"outputs":[{"data":{"image/png":"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","text/plain":["<pyannote.core.feature.SlidingWindowFeature at 0x7fd885eface0>"]},"execution_count":19,"metadata":{},"output_type":"execute_result"}],"source":["from pyannote.core import Segment\n","output = inference.crop(audio_in_memory, Segment(0, 20))\n","output"]},{"cell_type":"markdown","metadata":{"id":"K_Z-ciLaTIbU"},"source":["## Offline use\n","\n","Gating models allows [me](https://herve.niderb.fr) to know a bit more about `pyannote.audio` user base and eventually help me write grant proposals to make `pyannote.audio` even better. Please fill this form as precisely as possible.\n","\n","For instance, before gating `pyannote/segmentation`, I had no idea that so many people were relying on it in production. Hint: sponsors are more than welcome! maintaining open source libraries is time consuming.\n","\n","That being said: this whole authentication process does not prevent you from using official `pyannote.audio` models offline (i.e. without going through the authentication process in every `docker run ...` or whatever you are using in production).\n","\n","* Step 1: download the `pytorch_model.bin` model\n","\n","![](assets/download-model.png)\n","\n","* Step 2: load the model"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"t_kZgFSSTIbV"},"outputs":[],"source":["# look ma: no hands!\n","offline_model = Model.from_pretrained(\"pytorch_model.bin\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"wBkIFwR-TIbV"},"outputs":[],"source":["# just checking weights are the same...\n","import torch\n","for weights, offline_weights in zip(model.parameters(), offline_model.parameters()):\n","    assert torch.equal(weights, offline_weights)"]}],"metadata":{"accelerator":"GPU","colab":{"gpuType":"T4","provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.13"},"vscode":{"interpreter":{"hash":"36a3a48a52702f18671693adf589423ec3f7db45d50f6ee539f1b0696bb58d43"}},"widgets":{"application/vnd.jupyter.widget-state+json":{"01a79756e1104be0bcbe1d233677d605":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"09ee64808a5c431b928066a4cb287a78":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"0c537fef94bd4a3d8c42d981a70ea35b":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_ecbb880cf0044404ab9bfc5995656807","placeholder":"​","style":"IPY_MODEL_79287ffea49a4e4a80191b1157de15cc","value":"\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"}},"0e04a45510f346b8ab3c465b10ccdfd2":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"LabelModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_bf5c88fe90f0462b95aa8a81467c1e9d","placeholder":"​","style":"IPY_MODEL_09ee64808a5c431b928066a4cb287a78","value":"Connecting..."}},"1a30ac8b519948bbad72886049b53d55":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"2b91f4b11d5848c0b6795b649bc2d7bc":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"LabelModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_57cf64e9c70e4057a76c2f3fb1e9b191","placeholder":"​","style":"IPY_MODEL_5e90e4818f1f43f2aa4714e0e40dc15d","value":"Your token has been saved to /root/.cache/huggingface/token"}},"2d1965df902b4b7eb6e4e28e44d6e32b":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"CheckboxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"CheckboxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"CheckboxView","description":"Add token as git credential?","description_tooltip":null,"disabled":false,"indent":true,"layout":"IPY_MODEL_416ffb7703b1404ab1c19c6b1ecafb4c","style":"IPY_MODEL_5be7421c575d41128d0675dc9abbc196","value":true}},"416ffb7703b1404ab1c19c6b1ecafb4c":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"47da80658de14604a7cc5268b951c172":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"49cb317b141a43b7b8ce342e2d62ab03":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"52a4a1aab39741f2a0499428f07a4c25":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"LabelModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_01a79756e1104be0bcbe1d233677d605","placeholder":"​","style":"IPY_MODEL_990375a830eb4cd79c69ad78b9ac685b","value":"Token is valid (permission: write)."}},"53919e13e42441d9b8cf5eb4f2effe96":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"57cf64e9c70e4057a76c2f3fb1e9b191":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"5be7421c575d41128d0675dc9abbc196":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"5e90e4818f1f43f2aa4714e0e40dc15d":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"73915caf6d1042ca9a27853986217ae2":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"PasswordModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"PasswordModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"PasswordView","continuous_update":true,"description":"Token:","description_tooltip":null,"disabled":false,"layout":"IPY_MODEL_47da80658de14604a7cc5268b951c172","placeholder":"​","style":"IPY_MODEL_c7fbfffbbc304f0ba025e03beb8f638a","value":""}},"79287ffea49a4e4a80191b1157de15cc":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"79d55946b3764666a0b57a72722f6c19":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":"center","align_self":null,"border":null,"bottom":null,"display":"flex","flex":null,"flex_flow":"column","grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":"50%"}},"8b3353af24074ce5b5d2d9b162c61062":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"988c83c85f7d44d0be949de6eedcf977":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"990375a830eb4cd79c69ad78b9ac685b":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a73cecb8608f491e8f996c5114df4d0f":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"VBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"VBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"VBoxView","box_style":"","children":["IPY_MODEL_52a4a1aab39741f2a0499428f07a4c25","IPY_MODEL_f23cc133109c4ecb9b383f118bcc71aa","IPY_MODEL_2b91f4b11d5848c0b6795b649bc2d7bc","IPY_MODEL_b437981acb894f97ad45daaebe2734c7"],"layout":"IPY_MODEL_79d55946b3764666a0b57a72722f6c19"}},"abc23089f4ef4d2a9f8a104fb1dba14a":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b2e03b10050d46548932f429bcc18d81":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ButtonModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ButtonModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ButtonView","button_style":"","description":"Login","disabled":false,"icon":"","layout":"IPY_MODEL_8b3353af24074ce5b5d2d9b162c61062","style":"IPY_MODEL_cd40e31c191044b7a0f8fa4694ad6380","tooltip":""}},"b437981acb894f97ad45daaebe2734c7":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"LabelModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_fb027db34fd740c2a4758d650ae3f73c","placeholder":"​","style":"IPY_MODEL_1a30ac8b519948bbad72886049b53d55","value":"Login successful"}},"bc10c6804346449b8e349728a1acb8d2":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_988c83c85f7d44d0be949de6eedcf977","placeholder":"​","style":"IPY_MODEL_53919e13e42441d9b8cf5eb4f2effe96","value":"<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"}},"bf5c88fe90f0462b95aa8a81467c1e9d":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c7fbfffbbc304f0ba025e03beb8f638a":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"cd40e31c191044b7a0f8fa4694ad6380":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ButtonStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ButtonStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","button_color":null,"font_weight":""}},"ecbb880cf0044404ab9bfc5995656807":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f23cc133109c4ecb9b383f118bcc71aa":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"LabelModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_49cb317b141a43b7b8ce342e2d62ab03","placeholder":"​","style":"IPY_MODEL_abc23089f4ef4d2a9f8a104fb1dba14a","value":"Your token has been saved in your configured git credential helpers (store)."}},"fb027db34fd740c2a4758d650ae3f73c":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}}}}},"nbformat":4,"nbformat_minor":0}