{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\"Open" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "# Training, fine-tuning, and transfer learning with pyannote.audio\n", "\n", "In this tutorial, you will learn how to use pyannote.audio to\n", "\n", "- train a voice activity detection model from scratch,\n", "- fine-tune a pretrained speaker segmentation model,\n", "- perform transfer learning (from speaker segmentation to overlapped speech detection)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Tutorial setup" ] }, { "cell_type": "markdown", "metadata": { "id": "72ECjKLknm8D" }, "source": [ "### `Google Colab` setup" ] }, { "cell_type": "markdown", "metadata": { "id": "mBBNyENbofJ4" }, "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 a mini version of the `AMI` corpus." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "executionInfo": { "elapsed": 68165, "status": "ok", "timestamp": 1704810976973, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "Luhkk8D4oiir", "outputId": "7f43b6e3-8dba-40c1-a9e9-5b3ae4ddc891" }, "outputs": [], "source": [ "!pip install -qq pyannote.audio==3.1.1\n", "!pip install -qq ipython==7.34.0\n", "!git clone https://github.com/pyannote/AMI-diarization-setup.git\n", "%cd ./AMI-diarization-setup/pyannote/\n", "!bash ./download_ami_mini.sh\n", "%cd /content" ] }, { "cell_type": "markdown", "metadata": { "id": "VWo84u4ypEMc" }, "source": [ "⚠ Restart the runtime (Runtime > Restart session)." ] }, { "cell_type": "markdown", "metadata": { "id": "zmnD8CUUnt1N" }, "source": [ "### Non `Google Colab` setup" ] }, { "cell_type": "markdown", "metadata": { "id": "HS7SxeZkoth1" }, "source": [ "If you are not using `Colab`, this tutorial assumes that\n", "* `pyannote.audio` has been installed\n", "* the [AMI corpus](https://groups.inf.ed.ac.uk/ami/corpus/) has already been [setup for use with `pyannote`](https://github.com/pyannote/AMI-diarization-setup/tree/main/pyannote)\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "executionInfo": { "elapsed": 810, "status": "ok", "timestamp": 1704811019354, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "67whHDb3pOIe" }, "outputs": [], "source": [ "# preparing notebook for visualization purposes\n", "# (only show outputs between t=180s and t=240s)\n", "from pyannote.core import notebook, Segment\n", "notebook.crop = Segment(210, 240)" ] }, { "cell_type": "markdown", "metadata": { "id": "z4-LIYSEnj5i" }, "source": [ "## Data preparation\n", "\n", "See [`pyannote.database` documentation](https://github.com/pyannote/pyannote-database#pyannote-database) to learn how to prepare your own dataset for training with `pyannote.audio`." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "8vw0KmndnX8L" }, "outputs": [], "source": [ "from pyannote.database import registry, FileFinder\n", "\n", "registry.load_database(\"AMI-diarization-setup/pyannote/database.yml\")\n", "ami = registry.get_protocol('AMI.SpeakerDiarization.mini')" ] }, { "cell_type": "markdown", "metadata": { "id": "69qydyg6nX8M" }, "source": [ "## Training a voice activity detection model from scratch" ] }, { "cell_type": "markdown", "metadata": { "id": "l0-I4_ApnX8N" }, "source": [ "Voice activity detection (VAD) is the task of detecting speech regions in a given audio stream or recording.\n", "\n", "We initialize a VAD *task* that describes how the model will be trained:\n", "\n", "* `ami` indicates that we will use files available in `ami.train()`.\n", "* `duration=2.` and `batch_size=128` indicates that the model will ingest batches of 128 two seconds long audio chunks." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "lFDktlSDnX8O" }, "outputs": [], "source": [ "from pyannote.audio.tasks import VoiceActivityDetection\n", "vad_task = VoiceActivityDetection(ami, duration=2.0, batch_size=128)" ] }, { "cell_type": "markdown", "metadata": { "id": "EZ0Kje3RnX8Q" }, "source": [ "We initialize one *model* with the `PyanNet` architecture used [in that paper](https://arxiv.org/abs/2104.04045). \n", "In particular, we increase the default stride of the initial `sincnet` feature extraction layer to `10`.\n", "\n", "The model is also provided with the task (`task=vad_task`) for which it is being trained:" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "executionInfo": { "elapsed": 226, "status": "ok", "timestamp": 1704811118255, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "kSfY8Y3fnX8R" }, "outputs": [], "source": [ "from pyannote.audio.models.segmentation import PyanNet\n", "vad_model = PyanNet(task=vad_task, sincnet={'stride': 10})" ] }, { "cell_type": "markdown", "metadata": { "id": "WCNd35YInX8T" }, "source": [ "Now that everything is ready, let's train with `pytorch-lightning`!" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "id": "ExlUZ6DonX8U" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "GPU available: False, used: False\n", "TPU available: False, using: 0 TPU cores\n", "IPU available: False, using: 0 IPUs\n", "HPU available: False, using: 0 HPUs\n", "\n", " | Name | Type | Params | In sizes | Out sizes \n", "---------------------------------------------------------------------------------------------------------------------\n", "0 | sincnet | SincNet | 42.6 K | [1, 1, 32000] | [1, 60, 115] \n", "1 | lstm | LSTM | 589 K | [1, 115, 60] | [[1, 115, 256], [[4, 1, 128], [4, 1, 128]]]\n", "2 | linear | ModuleList | 49.4 K | ? | ? \n", "3 | classifier | Linear | 129 | [1, 115, 128] | [1, 115, 1] \n", "4 | activation | Sigmoid | 0 | [1, 115, 1] | [1, 115, 1] \n", "5 | validation_metric | MetricCollection | 0 | ? | ? \n", "---------------------------------------------------------------------------------------------------------------------\n", "681 K Trainable params\n", "0 Non-trainable params\n", "681 K Total params\n", "2.728 Total estimated model params size (MB)\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "766125242dd74f4bbd958c0488de0aeb", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Sanity Checking: | | 0/? [00:00" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from pyannote.audio import Inference\n", "vad = Inference(vad_model)\n", "\n", "vad_probability = vad(test_file)\n", "vad_probability" ] }, { "cell_type": "markdown", "metadata": { "id": "vYf27Tg9nX8Z" }, "source": [ "Perfect voice activity detection output should look like that:" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "DRX0bew-nX8Z", "outputId": "77b43b35-ba67-4189-c588-43396ee49366" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ ", , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ])>" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "expected_output = test_file[\"annotation\"].get_timeline().support()\n", "expected_output" ] }, { "cell_type": "markdown", "metadata": { "id": "dzNs5vrUnX8a" }, "source": [ "## Fine-tuning a pretrained speaker segmentation model\n", "\n", "Speaker diarization is the task of partitioning a given audio stream of recording into according to the speaker identity.\n", "\n", "[`pyannote/segmentation`](https://huggingface.co/pyannote/segmentation-3.0) is a model that was pretrained to perform speaker diarization, but only locally, on 10s-long audio chunks.\n", "\n", "To load the speaker segmentation model,\n", "\n", "* accept the user conditions on [hf.co/pyannote/segmentation](https://hf.co/pyannote/segmentation-3.0).\n", "* login using `notebook_login` below" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 145, "referenced_widgets": [ "0c403a6fbba048a9a5388b71a0d83259", "b906b2359fa84291b3b78bcced4f3028", "8f7afdee0292401181bd477a89ee3069", "05b307b893b84133a376088787ababac", "c258b47039a243cabadd48de545542f2", "15ab3c58a6014beb9c7ba5e3f5bc0b77", "df65aff406cc4288806b278cf83fb7df", "31f30fd568f84363b8dea2d40f54885c", "f383e9d323c64c64b528266858d6595c", "772e6eb169d84fcb808957fd886a59d1", "dcf595ee01a248f895635ad054c8ce28", "385eecea5fca4494be7a0e2dc34110ca", "c742508bbe1e4f0f9ad385896afea5eb", "e7aa7e431546419792ff998e10c4bbe9", "0e04e5e88aae4f14838356c422ba7ed5", "20ba5327eef34c7fa20f9f247b9042b1", "cc9cc24a3aea416a99897cf0c617f225", "98b09e7bb5d14a9d8c85e52f54c9c6cf", "50ed1cf2997e4929853964103bb7552c", "4bf2285d01ca4f6c86a117f73972c7e7", "d1063e27f20648ff9a43fede902a08a4", "3b133fae87364dcc89a34ed147995807", "e50f15a31e4543219ed038b88132d905", "6b641f7304e943d7b53466fc5aa376a2", "8865c7d7d01040329de63b6a13e0fdff", "3e816698f9f54bc28712b7e0a1f1dba5", "bd36d10136344d4b9965557a8783c5f1", "d1f2777676bf4237947a0e42ff7da6de", "245a4232482547579a72d10243664849", "d072771073ed479b8e16cd9e5b9262c7", "bf24ab0141ce423393972b66c6d09f94", "bd2757c3b84f4ec283b083d64ea52d7a" ] }, "executionInfo": { "elapsed": 362, "status": "ok", "timestamp": 1704811300494, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "peG_1xclnX8b", "outputId": "3befc3a8-d54c-4a4b-9b40-2ce1229eeaa5" }, "outputs": [], "source": [ "from huggingface_hub import notebook_login\n", "notebook_login()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 81, "referenced_widgets": [ "84262babb03c4f7dab14b35637e29c31", "35f0b383bafc4425a27f36bc95874430", "f3d067b1a56849c19c933fb3380386b6", "5fb8f440470f4492a5a7a009760a0926", "c8348fafe0de405da831284cb39af5cc", "b3a67d2e0c14492788806bb221761174", "2f70dbe63df14dd18224e2bcb35b6e38", "0f59d4fccfc045b89337b4b4254de7c3", "c3204d520d604179923e93e0a9bfd395", "1cc4aeb271f4441d83c3227a0fef607e", "dd4a788ac0cb44ce93b6c001449d5d45", "bcccc0031f7245a394abc3aee4a6e1c2", "69c5b722ba3746aa80d87b3ee9fea08e", "ef96f5501bbb4a55b3aedac70d1261b5", "2d26c7ece1fe40178ab85f3d14408532", "693fc1fa7fd746ce8a089f3fd6683b51", "fd5fe3ad4e43456c896ca45ff6a6f155", "b92e36c0853f40738b51b8ef39f0377d", "8336d24b72414718b82c3195897ee896", "469ce1b8998a4d998d42fbea5f431781", "e7045e323ec947b3b354ffc61365f4cd", "b86e1bdb52414bfab9798b661e3e096d" ] }, "executionInfo": { "elapsed": 3764, "status": "ok", "timestamp": 1704811326591, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "wO1fXdA9nX8c", "outputId": "5933da6e-d984-4ab1-9041-62b3d9c5a909" }, "outputs": [], "source": [ "from pyannote.audio import Model\n", "pretrained = Model.from_pretrained(\"pyannote/segmentation-3.0\", token=True)" ] }, { "cell_type": "markdown", "metadata": { "id": "zm1-d-IsnX8d" }, "source": [ "Let's visualize how it performs on our test file:" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "id": "beFpRrN-nX8d" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "spk_probability = Inference(pretrained, step=2.5)(test_file)\n", "spk_probability" ] }, { "cell_type": "markdown", "metadata": { "id": "hrJ9pDbTnX8e" }, "source": [ "A perfect output would look like that:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "id": "bLcE98G4nX8f", "outputId": "7bb6ed3d-8076-4ebf-fa89-95a8c5943d27" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_file[\"annotation\"].discretize(notebook.crop, resolution=0.010)" ] }, { "cell_type": "markdown", "metadata": { "id": "9DY3NIY5nX8f" }, "source": [ "We are going to fine-tune this pretrained model on the AMI dataset:" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "executionInfo": { "elapsed": 1183, "status": "ok", "timestamp": 1704811457994, "user": { "displayName": "Clément PAGES", "userId": "11757386314069785178" }, "user_tz": -60 }, "id": "GJ2BWqqknX8g" }, "outputs": [], "source": [ "from pyannote.audio.tasks import SpeakerDiarization\n", "seg_task = SpeakerDiarization(ami, duration=10.0, max_speakers_per_chunk=3, max_speakers_per_frame=2)" ] }, { "cell_type": "markdown", "metadata": { "id": "y6e77EJ-nX8g" }, "source": [ "To check that fine-tuning was actually helpful, we need to evaluate the performance of the pretrained model, and compute the average local diarization error rate on a 10s window sliding over the whole test set. To do so, we need to create a helper function:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "id": "XxJs0DtCnX8h" }, "outputs": [], "source": [ "def test(model, protocol, subset=\"test\"):\n", " from pyannote.audio.utils.signal import binarize\n", " from pyannote.audio.utils.metric import DiscreteDiarizationErrorRate\n", " from pyannote.audio.pipelines.utils import get_devices\n", "\n", " (device,) = get_devices(needs=1)\n", " metric = DiscreteDiarizationErrorRate()\n", " files = list(getattr(protocol, subset)())\n", "\n", " inference = Inference(model, device=device)\n", "\n", " for file in files:\n", " reference = file[\"annotation\"]\n", " hypothesis = binarize(inference(file))\n", " uem = file[\"annotated\"]\n", " _ = metric(reference, hypothesis, uem=uem)\n", "\n", " return abs(metric)" ] }, { "cell_type": "markdown", "metadata": { "id": "Nkdm0dR0nX8h" }, "source": [ "We can then evaluate the model and see its local DER:" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "id": "LH0CGdmnnX8i", "outputId": "b07ba927-6f23-403a-d70b-74cf8685df06" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Local DER (pretrained) = 19.7%\n" ] } ], "source": [ "der_pretrained = test(model=pretrained, protocol=ami, subset=\"test\")\n", "print(f\"Local DER (pretrained) = {der_pretrained * 100:.1f}%\")" ] }, { "cell_type": "markdown", "metadata": { "id": "qUCdup8QnX8i" }, "source": [ "Next, we prepare the model for fine-tuning, simply by overriding its `task` attribute..." ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "id": "5i5Bv-7enX8j" }, "outputs": [], "source": [ "from copy import deepcopy\n", "finetuned = deepcopy(pretrained)\n", "finetuned.task = seg_task" ] }, { "cell_type": "markdown", "metadata": { "id": "nDPEYDZKnX8j" }, "source": [ "... and we train it (for just one epoch)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "colab": { "referenced_widgets": [ "", "634877439d6744d88223cfd1313e5fc1" ] }, "id": "AIUsJ3MqnX8k", "outputId": "6078a5dd-5cb2-4780-db4e-e3516d1cce8e" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "GPU available: False, used: False\n", "TPU available: False, using: 0 TPU cores\n", "IPU available: False, using: 0 IPUs\n", "HPU available: False, using: 0 HPUs\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n", " | 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", "5 | powerset | Powerset | 0 | ? | ? \n", "6 | validation_metric | MetricCollection | 0 | ? | ? \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)\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "fc1c93f0b95649b1ae7a7135c9c04d62", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Sanity Checking: | | 0/? [00:00" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Inference('pyannote/segmentation-3.0', token=True, step=2.5)(test_file)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "id": "DvpRY7H1nX82", "outputId": "ce284d08-e0f1-4a58-da1e-0b7c62fa2f31" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_file[\"annotation\"]" ] }, { "cell_type": "markdown", "metadata": { "id": "hjw4nIE7nX83" }, "source": [ "Let's update the model so that it specifically addresses overlapped speech detection. \n", "This is achieved very simply by updating the `task` attribute..." ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "id": "xhmDk1qJnX83" }, "outputs": [], "source": [ "from pyannote.audio.tasks import OverlappedSpeechDetection\n", "osd_task = OverlappedSpeechDetection(ami, duration=2.0)\n", "\n", "osd_model = Model.from_pretrained(\"pyannote/segmentation-3.0\", token=True)\n", "osd_model.task = osd_task" ] }, { "cell_type": "markdown", "metadata": { "id": "wbb0MeQanX84" }, "source": [ "... optionally freeezing a bunch of layers..." ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "id": "tuE1xNjunX84", "outputId": "2211d836-8bda-4550-a5e2-7646c764c0af" }, "outputs": [ { "data": { "text/plain": [ "['sincnet',\n", " 'sincnet.wav_norm1d',\n", " 'sincnet.conv1d',\n", " 'sincnet.conv1d.0',\n", " 'sincnet.conv1d.0.filterbank',\n", " 'sincnet.conv1d.1',\n", " 'sincnet.conv1d.2',\n", " 'sincnet.pool1d',\n", " 'sincnet.pool1d.0',\n", " 'sincnet.pool1d.1',\n", " 'sincnet.pool1d.2',\n", " 'sincnet.norm1d',\n", " 'sincnet.norm1d.0',\n", " 'sincnet.norm1d.1',\n", " 'sincnet.norm1d.2',\n", " 'lstm']" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "osd_model.freeze_up_to('lstm')" ] }, { "cell_type": "markdown", "metadata": { "id": "DrKqQyXonX85" }, "source": [ "... and training it:" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "colab": { "referenced_widgets": [ "", "17ca908b800f4d34841bc2c7d5ccdff3" ] }, "id": "z9PIQ4oUnX85", "outputId": "ed98a898-d9a2-4895-d523-9660abf79f1e" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "GPU available: False, used: False\n", "TPU available: False, using: 0 TPU cores\n", "IPU available: False, using: 0 IPUs\n", "HPU available: False, using: 0 HPUs\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n", " | Name | Type | Params | In sizes | Out sizes \n", "---------------------------------------------------------------------------------------------------------------------\n", "0 | sincnet | SincNet | 42.6 K | [1, 1, 32000] | [1, 60, 115] \n", "1 | lstm | LSTM | 1.4 M | [1, 115, 60] | [[1, 115, 256], [[8, 1, 128], [8, 1, 128]]]\n", "2 | linear | ModuleList | 49.4 K | ? | ? \n", "3 | classifier | Linear | 129 | [1, 115, 128] | [1, 115, 1] \n", "4 | activation | Sigmoid | 0 | [1, 115, 1] | [1, 115, 1] \n", "5 | validation_metric | MetricCollection | 0 | ? | ? \n", "---------------------------------------------------------------------------------------------------------------------\n", "49.5 K Trainable params\n", "1.4 M Non-trainable params\n", "1.5 M Total params\n", "5.890 Total estimated model params size (MB)\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "7a9dfccd597f477bb2990e2746433375", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Sanity Checking: | | 0/? [00:00" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from pyannote.audio.utils.signal import binarize\n", "binarize(Inference(osd_model)(test_file))" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "id": "P_7CB2wgnX87", "outputId": "a5e3a05f-8695-4880-9380-fbde264ca06f" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAABjwAAADyCAYAAAD5q2z1AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAfgElEQVR4nO3de5RV5X038O8M14nMDHdGFNSoUVxRg5cqJmYpRUAxS1oTl8ZqJC7NBbFiLo2uVPuaxlhNtbWJsc0yaGo1pmm9tkCoEK1KCBLxFm8YXV5gIIAwgIow7PcPX+ftFJQB5nDY4+ez1llr5pzn7P17zp75zTPznbN3TVEURQAAAAAAAEqsttoFAAAAAAAA7CiBBwAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsBjC84555zU1NRsdlu0aFHOOeecTJw4catjx48f3zbm7bffzuTJkzNgwID06dMnp556apYuXdpun/Pnz88f//Efp2/fvunXr1/GjRuXxx9/vN2YmTNn5uijj059fX0GDRqUU089NS+//HIlX4pS25bjmCSvvvpqvvjFL2bo0KHp2bNn9tprr/z5n/95VqxY0W5cURS57LLLsvvuu6euri5jxozJCy+80G7M888/n1NOOSUDBw5MQ0NDPvWpT2XOnDntxtx///055phjUl9fn6ampvzFX/xFNm7cWJHXAgAAAACgq6tK4NG6YsVOvW2P8ePHZ8mSJe1u++yzT4fH3n777W2PT506Nffee2/+9V//NQ888EAWL16cP/3TP217fO3atRk/fnyGDx+eefPm5aGHHkp9fX3GjRuXDRs2JEleeumlnHLKKRk9enQWLlyYmTNnZvny5e22s7O9se6dnXbbXh09jr///e9zxBFH5IUXXsjtt9+eRYsW5cYbb8z999+fUaNGZeXKlW1jr7766lx//fW58cYbM2/evOy2224ZN25c3n777bYxJ598cjZu3JjZs2dnwYIFOfTQQ3PyySenubk5SfL444/npJNOyvjx4/PYY4/ljjvuyD333JNvfetb2z1XAAAAAIAPs5qiKIqdvdPX9xi2U/e3x+uvbtP4c845J6tWrcpdd9211cc+aGySrF69OoMGDcptt92Wz372s0mSZ599NiNGjMjcuXNz9NFH59FHH82RRx6ZV155JcOGvfvaPPnkkznkkEPywgsvZL/99ssvfvGLnHHGGVm/fn1qa9/Nqe69996ccsopWb9+fXr06LFNc+wMR18+c6ft69f/Z9w2P2dbjuOJJ56Yp556Ks8//3zq6uraxjU3N2fffffN2WefnR/96EcpiiJDhw7N1772tXz9619P8u4xHjJkSG6++eacfvrpWb58eQYNGpQHH3wwxx57bJJkzZo1aWhoyKxZszJmzJhceumlmTVrVubPn9+2r3vvvTennXZali1blvr6+m2eLwAAAADAh5lTWlXYggULsmHDhowZM6btvgMPPDDDhw/P3LlzkyQHHHBABgwYkJtuuinvvPNO3nrrrdx0000ZMWJE9t577yTJ4Ycfntra2kybNi2tra1ZvXp1/vmf/zljxoypStjRlaxcuTIzZ87MV7/61XZhR5I0NTXlzDPPzB133JGiKPLSSy+lubm53fFsbGzMUUcd1XY8BwwYkAMOOCA//elPs27dumzcuDH/+I//mMGDB+fwww9Pkqxfvz69e/dut6+6urq8/fbbWbBgQYVnDAAAAADQ9Qg83sd9992XPn36tN0+97nPdXhsnz59cuWVVyZ59x0CPXv2TN++fds9Z8iQIW2nN6qvr8+vfvWr3Hrrramrq0ufPn0yY8aMTJ8+Pd27d0+S7LPPPvnlL3+ZSy+9NL169Urfvn3z2muv5ec//3llXoAuoiPH8YUXXkhRFBkxYsQWtzFixIi88cYb+cMf/tB2zIYMGdJuzP88njU1Nfmv//qvPPbYY6mvr0/v3r1z7bXXZsaMGenXr1+SZNy4cXnkkUdy++23p7W1Na+//nquuOKKJMmSJUs6bf4AAAAAAB8WAo/3cfzxx2fhwoVtt+uvv77DYxcuXJgvf/nLHd7XW2+9lXPPPTef/OQn8+tf/zoPP/xwPv7xj2fChAl56623krwbnJx33nn5whe+kPnz5+eBBx5Iz54989nPfjZVOCtZaWzLceys17EoikyePDmDBw/Of//3f+c3v/lNJk6cmM985jNtYcbYsWNzzTXX5Mtf/nJ69eqVj33sYznppJOSpO2UZQAAAAAAdFz3auy06YmF1djtNtltt92y33777fDYpqamvPPOO1m1alW7d3ksXbo0TU1NSZLbbrstL7/8cubOndv2x+7bbrst/fr1y913353TTz89P/zhD9PY2Jirr766bRu33nprhg0blnnz5uXoo4/ezpluv+nfPH6n73NbdeQ47rfffqmpqckzzzyTP/mTP9ns8WeeeSb9+vXLoEGDsnbt2iTvHr/dd9+9bczSpUvziU98Ikkye/bs3HfffXnjjTfS0NCQJLnhhhsya9as3HLLLW0XJr/44oszderULFmyJP369cvLL7+cSy65JB/96Ec7Y+oAAAAAAB8qVQk8ug0YUI3dVsXhhx+eHj165P7778+pp56aJHnuuefyyiuvZNSoUUmSN998M7W1tampqWl73nufb9q0qd2Y/6lbt25J0jZmZ+u3W8+q7LezDRgwICeccEJuuOGGTJ06dbOLlv/Lv/xLzj777NTU1GSfffZJU1NT7r///raAo6WlJfPmzctXvvKVJO8eq2Tzd2rU1tZudqxqamoydOjQJMntt9+eYcOG5bDDDqvUVAEAAAAAuiznzukE69evT3Nzc7vb8uXLk7x7Qetzzz03F198cebMmZMFCxZk0qRJGTVqVNu7Mk444YS88cYbmTx5cp555pk8/fTTmTRpUrp3757jj3/3XRQTJkzI/Pnzc8UVV+SFF17Ib3/720yaNCl77bVXRo4cWbW5dxU/+MEPsn79+owbNy4PPvhgXn311cyYMSMnnHBC9thjj3z3u99N8m5AcdFFF+Wv//qvc8899+TJJ5/M2WefnaFDh2bixIlJklGjRqVfv375whe+kMcffzzPP/98vvGNb+Sll17KhAkT2vZ5zTXX5Mknn8zTTz+d73znO7nqqqty/fXXtwVZAAAAAAB0nMCjE8yYMSO77757u9unPvWptsevu+66nHzyyTn11FPz6U9/Ok1NTfn3f//3tscPPPDA3HvvvXniiScyatSoHHvssVm8eHHbdpNk9OjRue2223LXXXdl5MiRGT9+fHr16pUZM2a0e0cC22f//ffPo48+mo9+9KM57bTTsu++++b888/P8ccfn7lz56Z///5tY7/5zW9mypQpOf/883PkkUdm7dq1mTFjRnr37p0kGThwYGbMmJG1a9dm9OjROeKII/LQQw/l7rvvzqGHHtq2nenTp+fYY4/NEUcckf/4j//I3Xff3RaaAAAAAACwbWoKV7wGAAAAAABKzjs8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwAAAAAAUHrdK7XhTZs2ZfHixamvr09NTU2ldgMAAAAAAJRAURRZs2ZNhg4dmtrazn8/RsUCj8WLF2fYsGGV2jwAAAAAAFBCr776avbcc89O327FAo/6+vok7xbe0NBQqd0AAAAAAAAl0NLSkmHDhrXlB52tYoHHe6examhoEHgAAAAAAABJUrHLYLhoOQAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAoPYEHAAAAAABQegIPAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAovYoHHq3LllV6FwDQYa1Ll6blb69N69Kl1S6lKj7s86djdoWvk+Vr1ufHcxZl+Zr1VasBqsHXPgCUm5/lXY9jWi6VDzz+8IdK7wIAOqx12bKsufa6D20g/2GfPx2zK3ydLF+zPjf96kW/VPCh42sfAMrNz/KuxzEtF6e0AgAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKL3uld7BptUtaV2xotK7AYAO2bRqdbVL2CVsWrXaz2fe1670fbLmrQ15Y9071S4Ddpo1b22odgkAQCewju06rM/KpeKBx8pJX8yGWm8kAYBdyYrTz6h2CdAhU376aLVLAACAbWYdC9UhiQAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACi9il/Do/+0n2TAkUdUejcA0CEbfveM61ckGfCz29PjoBHVLoNd1K70ffIPZx+R/Zrqq10G7DSLmtc45zcAdAHWsV2H9Vm5VDzwqG1sSLcBAyq9GwDokNa+jdUuYZdQ27fRz2fe1670fVJf1yP9dutZ7TJgp6mv61HtEgCATmAd23VYn5WLU1oBAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAovYoHHt0GDar0LgCgw7oNHpz6i6em2+DB1S6lKj7s86djdoWvk4H1vXLucftmYH2vqtUA1eBrHwDKzc/yrscxLZeaoiiKSmy4paUljY2NWb16dRoaGiqxCwAAAAAAoCQqnRs4pRUAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAoPYEHAAAAAABQegIPAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAoPYEHAAAAAABQegIPAAAAAACg9AQeAECpLV+zPj+esyjL16yvdimdpivOCbqK1qVL0/K316Z16dJql1JVXgcAAHZFAg8AoNSWr1mfm371YpcKB7rinKCraF22LGuuvS6ty5ZVu5Sq8joAALArEngAAAAAAAClJ/AAAAAAAABKr3u1CwAA6Axr3tqQN9a9U+0yOsWatzZUuwRgKzatWp3WFSuqXUbVbFq1utolAADAZgQeAECXMOWnj1a7BOBDZMXpZ1S7BAAA4H9xSisAAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDScw0PAKBL+Iezj8h+TfXVLqNTLGpe45oksIsb8LPb0+OgEdUuo2o2/O4Z1zEBAGCXI/AAALqE+roe6bdbz2qX0Snq63pUuwRgK2r7NqbbgAHVLqNqWvs2VrsEAADYjFNaAQAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwBQagPre+Xc4/bNwPpe1S6l03TFOUFX0W3w4NRfPDXdBg+udilV5XUAAGBXVFMURVGJDbe0tKSxsTGrV69OQ0NDJXYBAAAAAACURKVzA+/wAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAoPYEHAAAAAABQegIPAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAAAAAAKD2BBwAAAAAAUHoCDwAAAAAAoPQEHgAAAAAAQOkJPAAAAAAAgNITeAAAAAAAAKUn8AAAAAAAAEpP4AEAAAAAAJSewAMAAAAAACg9gQcAAAAAAFB6Ag8AAAAAAKD0BB4AAAAAAEDpCTwAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKr3ulNlwURZKkpaWlUrsAAAAAAABK4r284L38oLNVLPBYsWJFkmTYsGGV2gUAAAAAAFAyK1asSGNjY6dvt2KBR//+/ZMkr7zySkUKB8qhpaUlw4YNy6uvvpqGhoZqlwNUgT4A6ANAohcA+gCQrF69OsOHD2/LDzpbxQKP2tp3Lw/S2NiogQFpaGjQC+BDTh8A9AEg0QsAfQD4//lBp2+3IlsFAAAAAADYiQQeAAAAAABA6VUs8OjVq1cuv/zy9OrVq1K7AEpALwD0AUAfABK9ANAHgMr3gZqiKIqKbBkAAAAAAGAncUorAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApbdNgcf3vve9HHnkkamvr8/gwYMzceLEPPfcc+3G/NM//VOOO+64NDQ0pKamJqtWrdpsOytXrsyZZ56ZhoaG9O3bN+eee27Wrl27QxMBdo7O6gN77713ampq2t2uuuqqnTQLYEdtrResXLkyU6ZMyQEHHJC6uroMHz48F154YVavXt1uO6+88komTJiQj3zkIxk8eHC+8Y1vZOPGjTt7OsB26Kw+8L/XAzU1NfnZz362s6cDbIeO/G7wpS99Kfvuu2/q6uoyaNCgnHLKKXn22WfbjbEegHLrrF5gTQDl1ZE+8J6iKHLiiSempqYmd911V7vHOmNNsE2BxwMPPJDJkyfn17/+dWbNmpUNGzZk7NixWbduXduYN998M+PHj8+ll176vts588wz8/TTT2fWrFm577778uCDD+b888/fpsKB6uisPpAkV1xxRZYsWdJ2mzJlSqXLBzrJ1nrB4sWLs3jx4nz/+9/PU089lZtvvjkzZszIueee27aN1tbWTJgwIe+8804eeeSR3HLLLbn55ptz2WWXVWtawDbojD7wnmnTprVbE0ycOHEnzwbYHh353eDwww/PtGnT8swzz2TmzJkpiiJjx45Na2trEusB6Ao6oxe8x5oAyqkjfeA9f/d3f5eamprN7u+0NUGxA5YtW1YkKR544IHNHpszZ06RpHjjjTfa3f+73/2uSFLMnz+/7b7p06cXNTU1xeuvv74j5QBVsD19oCiKYq+99iquu+66yhcI7BQf1Ave8/Of/7zo2bNnsWHDhqIoiuI///M/i9ra2qK5ubltzI9+9KOioaGhWL9+fcVrBjrX9vSBoiiKJMWdd965EyoEKq0jfeDxxx8vkhSLFi0qisJ6ALqi7ekFRWFNAF3J+/WBxx57rNhjjz2KJUuWbPY931lrgh26hsd7b0fv379/h58zd+7c9O3bN0cccUTbfWPGjEltbW3mzZu3I+UAVbA9feA9V111VQYMGJCRI0fmmmuu8bZ1KLGO9ILVq1enoaEh3bt3T/LumuDggw/OkCFD2saMGzcuLS0tefrppytbMNDptqcPvGfy5MkZOHBg/uiP/ig/+clPUhRFRWsFKmNrfWDdunWZNm1a9tlnnwwbNiyJ9QB0RdvTC95jTQBdw5b6wJtvvpnPf/7z+eEPf5impqbNntNZa4LuWx+yZZs2bcpFF12UT37yk/n4xz/e4ec1Nzdn8ODB7Yvo3j39+/dPc3Pz9pYDVMH29oEkufDCC3PYYYelf//+eeSRR3LJJZdkyZIlufbaaytULVApHekFy5cvz3e+8512p7Bsbm5ut5BJ0va5NQGUy/b2geTdU1yOHj06H/nIR/LLX/4yX/3qV7N27dpceOGFO6N0oJN8UB+44YYb8s1vfjPr1q3LAQcckFmzZqVnz55JrAegq9neXpBYE0BX8X59YOrUqTnmmGNyyimnbPF5nbUm2O7AY/LkyXnqqafy0EMPbe8mgJLbkT5w8cUXt318yCGHpGfPnvnSl76U733ve+nVq1dnlglU2NZ6QUtLSyZMmJCDDjoof/VXf7VziwN2ih3pA3/5l3/Z9vHIkSOzbt26XHPNNf64ASXzQX3gzDPPzAknnJAlS5bk+9//fk477bQ8/PDD6d27dxUqBSppR3qBNQF0DVvqA/fcc09mz56dxx57rOL7365TWl1wwQW57777MmfOnOy5557b9NympqYsW7as3X0bN27MypUrt/hWFmDXtCN9YEuOOuqobNy4MS+//PKOFwfsNFvrBWvWrMn48eNTX1+fO++8Mz169Gh7rKmpKUuXLm03/r3PrQmgPHakD2zJUUcdlddeey3r16+vVMlAJ9taH2hsbMz++++fT3/60/nFL36RZ599NnfeeWcS6wHoSnakF2yJNQGUz/v1gdmzZ+fFF19M3759071797ZT3J566qk57rjjknTemmCbAo+iKHLBBRfkzjvvzOzZs7PPPvtsy9OTJKNGjcqqVauyYMGCtvtmz56dTZs25aijjtrm7QE7V2f0gS1ZuHBhamtrNzvlHbBr6kgvaGlpydixY9OzZ8/cc889m/0X56hRo/Lkk0+2+0eIWbNmpaGhIQcddFDF5wDsmM7oA1uycOHC9OvXzzs+oQS253eDoihSFEXbHzCtB6D8OqMXbIk1AZTH1vrAt771rTzxxBNZuHBh2y1JrrvuukybNi1J560JtumUVpMnT85tt92Wu+++O/X19W3nzmpsbExdXV2Sd8+n1dzcnEWLFiVJnnzyydTX12f48OHp379/RowYkfHjx+e8887LjTfemA0bNuSCCy7I6aefnqFDh25LOUAVdEYfmDt3bubNm5fjjz8+9fX1mTt3bqZOnZo/+7M/S79+/ao2N6DjttYL3vsj55tvvplbb701LS0taWlpSZIMGjQo3bp1y9ixY3PQQQflrLPOytVXX53m5uZ8+9vfzuTJk/1SAyXQGX3g3nvvzdKlS3P00Uend+/emTVrVq688sp8/etfr+bUgA7aWh/4/e9/nzvuuCNjx47NoEGD8tprr+Wqq65KXV1dTjrppCSxHoAuoDN6gTUBlNvW+kBTU9MW36UxfPjwtnCk09YExTZIssXbtGnT2sZcfvnlWx2zYsWK4owzzij69OlTNDQ0FJMmTSrWrFmzLaUAVdIZfWDBggXFUUcdVTQ2Nha9e/cuRowYUVx55ZXF22+/XZ1JAdtsa71gzpw57zvmpZdeatvOyy+/XJx44olFXV1dMXDgwOJrX/tasWHDhupMCtgmndEHpk+fXnziE58o+vTpU+y2227FoYceWtx4441Fa2tr9SYGdNjW+sDrr79enHjiicXgwYOLHj16FHvuuWfx+c9/vnj22Wfbbcd6AMqtM3qBNQGUW0f+Xril59x5553t7uuMNUHN/9s4AAAAAABAaW3XRcsBAAAAAAB2JQIPAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlJ7AAwAA2GHnnHNOJk6cWO0yAACAD7Hu1S4AAADYtdXU1Hzg45dffnn+/u//PkVR7KSKAAAANifwAAAAPtCSJUvaPr7jjjty2WWX5bnnnmu7r0+fPunTp081SgMAAGjjlFYAAMAHampqars1Njampqam3X19+vTZ7JRWxx13XKZMmZKLLroo/fr1y5AhQ/LjH/8469aty6RJk1JfX5/99tsv06dPb7evp556KieeeGL69OmTIUOG5Kyzzsry5ct38owBAIAyEngAAAAVccstt2TgwIH5zW9+kylTpuQrX/lKPve5z+WYY47Jb3/724wdOzZnnXVW3nzzzSTJqlWrMnr06IwcOTKPPvpoZsyYkaVLl+a0006r8kwAAIAyEHgAAAAVceihh+bb3/529t9//1xyySXp3bt3Bg4cmPPOOy/7779/LrvssqxYsSJPPPFEkuQHP/hBRo4cmSuvvDIHHnhgRo4cmZ/85CeZM2dOnn/++SrPBgAA2NW5hgcAAFARhxxySNvH3bp1y4ABA3LwwQe33TdkyJAkybJly5Ikjz/+eObMmbPF64G8+OKL+djHPlbhigEAgDITeAAAABXRo0ePdp/X1NS0u6+mpiZJsmnTpiTJ2rVr85nPfCZ/8zd/s9m2dt999wpWCgAAdAUCDwAAYJdw2GGH5d/+7d+y9957p3t3v6oAAADbxjU8AACAXcLkyZOzcuXKnHHGGZk/f35efPHFzJw5M5MmTUpra2u1ywMAAHZxAg8AAGCXMHTo0Dz88MNpbW3N2LFjc/DBB+eiiy5K3759U1vrVxcAAOCD1RRFUVS7CAAAAAAAgB3h36QAAAAAAIDSE3gAAAAAAAClJ/AAAAAAAABKT+ABAAAAAACUnsADAAAAAAAoPYEHAAAAAABQegIPAAAAAACg9AQeAAAAAABA6Qk8AAAAAACA0hN4AAAAAAAApSfwAAAAAAAASk/gAQAAAAAAlN7/Bcs45RiRI+F2AAAAAElFTkSuQmCC", "text/plain": [ "" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_file[\"annotation\"]" ] }, { "cell_type": "markdown", "metadata": { "id": "A4OM7DzwnX88" }, "source": [ "## Going further\n", "\n", "This tutorial only scratched the surface of the training API.\n", "\n", "Every task supports an `augmentation` parameter for training with data augmentation via [`torch-audiomentations`](https://github.com/asteroid-team/torch-audiomentations) library:\n", "\n", "```python\n", "from torch_audiomentations import AddBackgroundNoise\n", "augmentation = AddBackgroundNoise(\"/path/to/background/noise/directory\")\n", "vad_task = VoiceActivityDetection(ami, augmentation=augmentation)\n", "```\n", "\n", "We also benefit from all the nice things [`pytorch-lightning`](https://lightning.ai/docs/pytorch/stable/) has to offer (like multi-gpu training, for instance).\n", "\n", "```python\n", "trainer = Trainer(devices=4, accelerator=\"gpu\", strategy='ddp')\n", "trainer.fit(model)\n", "```\n", "\n", "Default optimizer (`Adam` with default parameters) is automatically set up for you. \n", "Customizing optimizer (and scheduler) requires overriding [`model.configure_optimizers`](https://lightning.ai/docs/pytorch/stable/common/lightning_module.html#configure-optimizers) method:\n", "\n", "```python\n", "from types import MethodType\n", "from torch.optim import SGD\n", "from torch.optim.lr_scheduler import ExponentialLR\n", "def configure_optimizers(self):\n", " return {\"optimizer\": SGD(self.parameters()),\n", " \"lr_scheduler\": ExponentialLR(optimizer, 0.9)}\n", "model.configure_optimizers = MethodType(configure_optimizers, model)\n", "trainer.fit(model)\n", "```" ] } ], "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" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "05b307b893b84133a376088787ababac": { "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_385eecea5fca4494be7a0e2dc34110ca", "style": "IPY_MODEL_c742508bbe1e4f0f9ad385896afea5eb", "value": true } }, "0c403a6fbba048a9a5388b71a0d83259": { "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_d1063e27f20648ff9a43fede902a08a4", "IPY_MODEL_3b133fae87364dcc89a34ed147995807", "IPY_MODEL_e50f15a31e4543219ed038b88132d905", "IPY_MODEL_6b641f7304e943d7b53466fc5aa376a2" ], "layout": "IPY_MODEL_df65aff406cc4288806b278cf83fb7df" } }, "0e04e5e88aae4f14838356c422ba7ed5": { "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": "" } }, "0f59d4fccfc045b89337b4b4254de7c3": { "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 } }, "15ab3c58a6014beb9c7ba5e3f5bc0b77": { "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_20ba5327eef34c7fa20f9f247b9042b1", "placeholder": "​", "style": "IPY_MODEL_cc9cc24a3aea416a99897cf0c617f225", "value": "\nPro Tip: 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. " } }, "1cc4aeb271f4441d83c3227a0fef607e": { "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 } }, "20ba5327eef34c7fa20f9f247b9042b1": { "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 } }, "245a4232482547579a72d10243664849": { "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 } }, "2d26c7ece1fe40178ab85f3d14408532": { "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_e7045e323ec947b3b354ffc61365f4cd", "placeholder": "​", "style": "IPY_MODEL_b86e1bdb52414bfab9798b661e3e096d", "value": " 399/399 [00:00<00:00, 22.1kB/s]" } }, "2f70dbe63df14dd18224e2bcb35b6e38": { "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": "" } }, "31f30fd568f84363b8dea2d40f54885c": { "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 } }, "35f0b383bafc4425a27f36bc95874430": { "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_b3a67d2e0c14492788806bb221761174", "placeholder": "​", "style": "IPY_MODEL_2f70dbe63df14dd18224e2bcb35b6e38", "value": "pytorch_model.bin: 100%" } }, "385eecea5fca4494be7a0e2dc34110ca": { "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 } }, "3b133fae87364dcc89a34ed147995807": { "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_bd36d10136344d4b9965557a8783c5f1", "placeholder": "​", "style": "IPY_MODEL_d1f2777676bf4237947a0e42ff7da6de", "value": "Your token has been saved in your configured git credential helpers (store)." } }, "3e816698f9f54bc28712b7e0a1f1dba5": { "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": "" } }, "469ce1b8998a4d998d42fbea5f431781": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "4bf2285d01ca4f6c86a117f73972c7e7": { "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": "" } }, "50ed1cf2997e4929853964103bb7552c": { "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 } }, "5fb8f440470f4492a5a7a009760a0926": { "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_1cc4aeb271f4441d83c3227a0fef607e", "placeholder": "​", "style": "IPY_MODEL_dd4a788ac0cb44ce93b6c001449d5d45", "value": " 5.91M/5.91M [00:00<00:00, 45.4MB/s]" } }, "693fc1fa7fd746ce8a089f3fd6683b51": { "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 } }, "69c5b722ba3746aa80d87b3ee9fea08e": { "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_fd5fe3ad4e43456c896ca45ff6a6f155", "placeholder": "​", "style": "IPY_MODEL_b92e36c0853f40738b51b8ef39f0377d", "value": "config.yaml: 100%" } }, "6b641f7304e943d7b53466fc5aa376a2": { "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_bf24ab0141ce423393972b66c6d09f94", "placeholder": "​", "style": "IPY_MODEL_bd2757c3b84f4ec283b083d64ea52d7a", "value": "Login successful" } }, "772e6eb169d84fcb808957fd886a59d1": { "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 } }, "8336d24b72414718b82c3195897ee896": { "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 } }, "84262babb03c4f7dab14b35637e29c31": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_35f0b383bafc4425a27f36bc95874430", "IPY_MODEL_f3d067b1a56849c19c933fb3380386b6", "IPY_MODEL_5fb8f440470f4492a5a7a009760a0926" ], "layout": "IPY_MODEL_c8348fafe0de405da831284cb39af5cc" } }, "8865c7d7d01040329de63b6a13e0fdff": { "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 } }, "8f7afdee0292401181bd477a89ee3069": { "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_772e6eb169d84fcb808957fd886a59d1", "placeholder": "​", "style": "IPY_MODEL_dcf595ee01a248f895635ad054c8ce28", "value": "" } }, "98b09e7bb5d14a9d8c85e52f54c9c6cf": { "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_50ed1cf2997e4929853964103bb7552c", "placeholder": "​", "style": "IPY_MODEL_4bf2285d01ca4f6c86a117f73972c7e7", "value": "Connecting..." } }, "b3a67d2e0c14492788806bb221761174": { "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 } }, "b86e1bdb52414bfab9798b661e3e096d": { "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": "" } }, "b906b2359fa84291b3b78bcced4f3028": { "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_31f30fd568f84363b8dea2d40f54885c", "placeholder": "​", "style": "IPY_MODEL_f383e9d323c64c64b528266858d6595c", "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" } }, "b92e36c0853f40738b51b8ef39f0377d": { "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": "" } }, "bcccc0031f7245a394abc3aee4a6e1c2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_69c5b722ba3746aa80d87b3ee9fea08e", "IPY_MODEL_ef96f5501bbb4a55b3aedac70d1261b5", "IPY_MODEL_2d26c7ece1fe40178ab85f3d14408532" ], "layout": "IPY_MODEL_693fc1fa7fd746ce8a089f3fd6683b51" } }, "bd2757c3b84f4ec283b083d64ea52d7a": { "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": "" } }, "bd36d10136344d4b9965557a8783c5f1": { "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 } }, "bf24ab0141ce423393972b66c6d09f94": { "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 } }, "c258b47039a243cabadd48de545542f2": { "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_e7aa7e431546419792ff998e10c4bbe9", "style": "IPY_MODEL_0e04e5e88aae4f14838356c422ba7ed5", "tooltip": "" } }, "c3204d520d604179923e93e0a9bfd395": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "c742508bbe1e4f0f9ad385896afea5eb": { "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": "" } }, "c8348fafe0de405da831284cb39af5cc": { "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 } }, "cc9cc24a3aea416a99897cf0c617f225": { "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": "" } }, "d072771073ed479b8e16cd9e5b9262c7": { "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": "" } }, "d1063e27f20648ff9a43fede902a08a4": { "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_8865c7d7d01040329de63b6a13e0fdff", "placeholder": "​", "style": "IPY_MODEL_3e816698f9f54bc28712b7e0a1f1dba5", "value": "Token is valid (permission: write)." } }, "d1f2777676bf4237947a0e42ff7da6de": { "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": "" } }, "dcf595ee01a248f895635ad054c8ce28": { "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": "" } }, "dd4a788ac0cb44ce93b6c001449d5d45": { "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": "" } }, "df65aff406cc4288806b278cf83fb7df": { "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%" } }, "e50f15a31e4543219ed038b88132d905": { "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_245a4232482547579a72d10243664849", "placeholder": "​", "style": "IPY_MODEL_d072771073ed479b8e16cd9e5b9262c7", "value": "Your token has been saved to /root/.cache/huggingface/token" } }, "e7045e323ec947b3b354ffc61365f4cd": { "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 } }, "e7aa7e431546419792ff998e10c4bbe9": { "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 } }, "ef96f5501bbb4a55b3aedac70d1261b5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8336d24b72414718b82c3195897ee896", "max": 399, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_469ce1b8998a4d998d42fbea5f431781", "value": 399 } }, "f383e9d323c64c64b528266858d6595c": { "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": "" } }, "f3d067b1a56849c19c933fb3380386b6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0f59d4fccfc045b89337b4b4254de7c3", "max": 5905440, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_c3204d520d604179923e93e0a9bfd395", "value": 5905440 } }, "fd5fe3ad4e43456c896ca45ff6a6f155": { "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 }