{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Audio Sentiment Classifier\n", "\n", "This notebook will walk you through using an agent, powered by AI, to take the sentiment of an audio clip, of a single speaker, to classify it in an Encord Workflow. Sentiment refers to the emotion portrayed by an audio clip.\n", "\n", "The agent in this example classifies sentiment into the emotional categories of: sad, happy, angry, neutral, disgust, fearful, surprised, and calm.\n", "\n", "### Requirements\n", "\n", "For this notebook you will need:\n", " - A Dataset containing seekable audio files in [Encord](https://app.encord.com/)\n", " - A [Huggingface](https://huggingface.co/) user access token.\n", "\n", "### Example Workflow\n", "The following Workflow shows how audio files can be pre-labelled with a sentiment classification. After sentiment classifications are applied, the labels are sent to a review stage. An example use case of this Workflow is reviewing the accuracy of a model.\n", "![Screenshot 2025-06-26 at 11.59.40.png](data:image/png;base64,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)\n", "\n", "After being labelled with a sentiment, the labels are sent to a review stage. An example use case of this workflow would be for checking the accuracy of a model before using in a wider project." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Installation\n", "Ensure the following libraries are installed:\n", " - `encord-agents` library.\n", " - `transformers` a huggingface library\n", " - `librosa`\n", " - `torch`\n", " - `numpy`" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip install encord-agents\n", "!pip install transformers\n", "!pip install librosa\n", "!pip install torch\n", "!pip install numpy" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Hugging Face Authentication\n", "\n", "Retrieve your Hugging Face API token for accessing models. The Hugging Face (User Access) token is an authentication key used for accessing models on the platform.\n", "\n", "> 💡 If running in colab, set the key in secrets under the name `HF_TOKEN`, you can find this menu in the left sidebar.\n", ">\n", ">If you are not running in a colab notebook, set the environment variable directly, this can be done with:\n", "```python\n", "os.environ[\"HF_TOKEN\"] = \"\"\"paste-user-access-token-here\"\"\"\n", "```" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from google.colab import userdata\n", "\n", "HF_TOKEN = userdata.get(\"HF_TOKEN\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Speech-emotion Model setup\n", "\n", "\n", "The following code does two things:\n", " 1. Imports the necessary libraries for the audio processing.\n", " 2. Prepares the variables we are going to use in our agent to classify audio clips." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import librosa\n", "import numpy as np\n", "import torch\n", "from transformers import AutoFeatureExtractor, AutoModelForAudioClassification\n", "\n", "model_id = \"firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3\"\n", "model = AutoModelForAudioClassification.from_pretrained(model_id)\n", "\n", "feature_extractor = AutoFeatureExtractor.from_pretrained(model_id, do_normalize=True)\n", "id2label = model.config.id2label" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Model Functions\n", "The following functions provide functionality for our agent to interface with the model.\n", " - `preprocess_audio` prepares the audio for processing by the model.\n", " - `predict_emotion` uses the model to predict the audio's sentiment.\n", "\n", " These functions were retrieved from Hugging Face, [here](https://huggingface.co/firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3#%F0%9F%9A%80-how-to-use)." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def preprocess_audio(audio_path, feature_extractor, max_duration=30.0):\n", " audio_array, sampling_rate = librosa.load(audio_path, sr=feature_extractor.sampling_rate)\n", "\n", " max_length = int(feature_extractor.sampling_rate * max_duration)\n", " if len(audio_array) > max_length:\n", " audio_array = audio_array[:max_length]\n", " else:\n", " audio_array = np.pad(audio_array, (0, max_length - len(audio_array)))\n", "\n", " inputs = feature_extractor(\n", " audio_array,\n", " sampling_rate=feature_extractor.sampling_rate,\n", " max_length=max_length,\n", " truncation=True,\n", " return_tensors=\"pt\",\n", " )\n", " return inputs" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def predict_emotion(audio_path, model, feature_extractor, id2label, max_duration=30.0):\n", " inputs = preprocess_audio(audio_path, feature_extractor, max_duration)\n", "\n", " device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", " model = model.to(device)\n", " inputs = {key: value.to(device) for key, value in inputs.items()}\n", "\n", " with torch.no_grad():\n", " outputs = model(**inputs)\n", "\n", " logits = outputs.logits\n", " predicted_id = torch.argmax(logits, dim=-1).item()\n", " predicted_label = id2label[predicted_id]\n", "\n", " return predicted_label" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Encord Authentication\n", "\n", "The Encord platform uses ssh-keys for authentication. For use of it with agents, the `ENCORD_SSH_KEY` needs to be set as an environment variable containing the raw content of the private key file.\n", "\n", "If you do not have an ssh key this [documentation](https://agents-docs.encord.com/authentication/) will guide you to create one.\n", "\n", "If you are running in colab, create a user secret called SSH_KEY and set it to your encord ssh key.\n", "\n", "> If you are **not** executing this in colab, set it directly as an environment variable with\n", ">\n", "> ```python\n", "os.environ['ENCORD_SSH_KEY'] = \"\"\"paste-ssh-key-here\"\"\"\n", "```" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import os\n", "\n", "os.environ[\"ENCORD_SSH_KEY\"] = userdata.get(\"SSH_KEY\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Imports & Variable Names\n", "\n", "The following script imports the necessary dependencies from the `encord` / `encord-agents` libraries to interact with the API so the agent work." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "from typing import Annotated\n", "\n", "from encord.objects.classification import Classification\n", "from encord.objects.ontology_labels_impl import LabelRowV2\n", "from encord.project import Project\n", "\n", "from encord_agents.core.dependencies.models import Depends\n", "from encord_agents.tasks import Runner\n", "from encord_agents.tasks.dependencies import dep_asset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The following variables need to be set:\n", "- `PROJECT_HASH`: Contains the id of **your** project, this is how the runner connects to your project later on.\n", "- `STAGE_ID`: Contains the id of the agent stage in **your** workflow, this is where the function we will create is run.\n", "- `SENTIMENT_CLASSIFIED_PATHWAY_NAME`: The name of the path to send the file on, this does not need to be changed if you have followed the workflow example" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "PROJECT_HASH = \"\"\n", "STAGE_ID = \"\"\n", "SENTIMENT_CLASSIFIED_PATHWAY_NAME = \"Sentiment Classified\"" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Ontology Structure\n", "\n", "For this project, the following ontology is appropriate to use.\n", "\n", "![Screenshot 2025-06-26 at 13.46.16.png](data:image/png;base64,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)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can use classifications and not objects as we are labelling the whole clip, not sections of it." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Defining the Runner\n", " The runner object is what we use to link our functions to our project." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "runner = Runner(project_hash=PROJECT_HASH)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Defining the Function\n", "The function is what is run on the agent stage in our workflow.\n", "\n", "The decorator `@runner.stage()` means that the function `classify_by_sentiment` runs at the appropriate agent stage and it passes in the parameters of `lr`, `asset` and `project` for us to use.\n", "\n", "The function is explained in greater depth with the comments in the script." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Common variables used to create Audio classifications in Encord\n", "radio_ontology_classification = runner.project.ontology_structure.get_child_by_title(\n", " title=\"emotion\", type_=Classification\n", ")\n", "\n", "# Collects attributes of the classifcation radio options and then creates a dictionary to\n", "# translate the label to an Option object for the API to accept.\n", "attr = radio_ontology_classification.attributes[0]\n", "dict_lbl_to_opt = {option.label: option for option in attr.options}" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "@runner.stage(STAGE_ID, overwrite=True)\n", "def classify_by_sentiment(lr: LabelRowV2, asset: Annotated[Path, Depends(dep_asset)]):\n", " # Using the model to predict the emotion\n", " predicted_emotion = predict_emotion(asset, model, feature_extractor, id2label)\n", "\n", " # Prepares an instance to use to add a classification to the audio.\n", " # As we're classifying audio, we need the range_only=True variable\n", " classification_instance = radio_ontology_classification.create_instance(range_only=True)\n", "\n", " # To determine which classifcation is added to the asset\n", " # [ dict_lbl_to_opt(\"sad\"), attr ] `attr` tells the API to focus\n", " # on top level classifications only\n", "\n", " match predicted_emotion:\n", " case \"sad\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"sad\"], attr)\n", " case \"happy\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"happy\"], attr)\n", " case \"angry\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"angry\"], attr)\n", " case \"neutral\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"neutral\"], attr)\n", " case \"disgust\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"disgust\"], attr)\n", " case \"fearful\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"fearful\"], attr)\n", " case \"surprised\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"surprised\"], attr)\n", " case \"calm\":\n", " classification_instance.set_answer(dict_lbl_to_opt[\"calm\"], attr)\n", "\n", " # Indicates that the whole audio should be classified, and old classifications should be overwritten\n", " classification_instance.set_for_frames()\n", " lr.add_classification_instance(classification_instance)\n", " lr.save()\n", "\n", " return SENTIMENT_CLASSIFIED_PATHWAY_NAME # Sentiment Classified Path" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Running the agent\n", "\n", "To run the agent in our Workflow, we can call the runner object." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "runner()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Outcome\n", "This AI-powered agent performs reliable sentiment and emotion classification on short, single-speaker audio clips. The Encord Workflow in this example shows how the model's accuracy can be evaluated with human review of its generated labels." ] } ], "metadata": { "colab": { "provenance": [], "toc_visible": true }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "02931787182345eabf9d3f784170058c": { "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": "" } }, "0d3604fca4c74e2583a85d9a28e0dc28": { "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 } }, "0ed9660807eb42e09266812f46de2522": { "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_de409483fac7461fabc7c67cc3a6bd07", "IPY_MODEL_28a3a3ff96904069bd7ec347a43a89dd", "IPY_MODEL_7e8f65c52e5845af9b561540117e4ff3" ], "layout": "IPY_MODEL_58b4656a8500444796e2b9df8b599a77" } }, "27520024e386438e9fc1a4caa4eba501": { "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 } }, "28a3a3ff96904069bd7ec347a43a89dd": { "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_844928ccbb074b37bf70e68fb0edab5e", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_381d5e9388ab4ef08e55cfdca68746b1", "value": 1 } }, "33d5573675d84d5781ab16e172409d1d": { "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 } }, "36e942b77f7a46979a0b7dce12c16386": { "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_7eec629d46c54a39808fa0eb1bd1755d", "IPY_MODEL_523731d364f74d6fb3a5cb5e19d49dac", "IPY_MODEL_e8648a9b28c043c4a76c4c81e207b3e0" ], "layout": "IPY_MODEL_4b2d4f2044f842a4b1798f97c0c3c32d" } }, "381d5e9388ab4ef08e55cfdca68746b1": { "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": "" } }, "4b2d4f2044f842a4b1798f97c0c3c32d": { "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 } }, "523731d364f74d6fb3a5cb5e19d49dac": { "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_a93f87450b1243b7ae971aea9a75cd34", "max": 2549249204, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_926c211d01fe4d1887f7d29d0d07f2d1", "value": 2549249204 } }, "58b4656a8500444796e2b9df8b599a77": { "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 } }, "599616631d70485bba118ddb0a6c0e6b": { "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_33d5573675d84d5781ab16e172409d1d", "max": 340, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_cba77ce9fa3d417d93b56dfba37f847b", "value": 340 } }, "630c9885c80e450ab32a452ac2946f16": { "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 } }, "6371a46b268a43e1baaa091655ff3fad": { "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 } }, "7232fb7ce0394b2a9e173657cf7e6c6f": { "model_module": "@jupyter-widgets/output", "model_module_version": "1.0.0", "model_name": "OutputModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/output", "_model_module_version": "1.0.0", "_model_name": "OutputModel", "_view_count": null, "_view_module": "@jupyter-widgets/output", "_view_module_version": "1.0.0", "_view_name": "OutputView", "layout": "IPY_MODEL_27520024e386438e9fc1a4caa4eba501", "msg_id": "", "outputs": [ { "data": { "text/html": "
 Executing agent `f94b2e24-5f2e-4059-97eb-ac891f8d4c41` (total: 0) ? 0:00:03\n Executing batch 0 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:02 ?   0%  \n
\n", "text/plain": "\u001b[32m⠧\u001b[0m Executing agent \u001b[35m`f94b2e24-5f2e-4059-97eb-ac891f8d4c41`\u001b[0m \u001b[36m(total: 0)\u001b[0m \u001b[31m?\u001b[0m \u001b[33m0:00:03\u001b[0m\n\u001b[32m⠧\u001b[0m Executing batch \u001b[36m0\u001b[0m \u001b[38;5;237m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[33m0:00:02\u001b[0m \u001b[31m?\u001b[0m \u001b[35m 0%\u001b[0m \n" }, "metadata": {}, "output_type": "display_data" } ] } }, "7e8f65c52e5845af9b561540117e4ff3": { "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_d6c4c5857d3f4e70bb45aa9dc1e4183a", "placeholder": "​", "style": "IPY_MODEL_90fac54906d841178dfa758641c22277", "value": " 1.56k/? [00:00<00:00, 80.5kB/s]" } }, "7eec629d46c54a39808fa0eb1bd1755d": { "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_83767d4c43df485bb94850281d609ecd", "placeholder": "​", "style": "IPY_MODEL_d63e697edfa04caabc6ec3ae4b5a49e2", "value": "model.safetensors: 100%" } }, "83767d4c43df485bb94850281d609ecd": { "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 } }, "844928ccbb074b37bf70e68fb0edab5e": { "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": "20px" } }, "8bfa67a031a7408285f7332ad6c626b4": { "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": "" } }, "90fac54906d841178dfa758641c22277": { "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": "" } }, "91e7c57605dc4b4e8941e40aad8dcc61": { "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_630c9885c80e450ab32a452ac2946f16", "placeholder": "​", "style": "IPY_MODEL_02931787182345eabf9d3f784170058c", "value": "preprocessor_config.json: 100%" } }, "926c211d01fe4d1887f7d29d0d07f2d1": { "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": "" } }, "a804df02bd1c4f6f987f20540b84c927": { "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 } }, "a93f87450b1243b7ae971aea9a75cd34": { "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 } }, "b9b0459ebe164a72b4fa1d5dc43edb43": { "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": "" } }, "cba77ce9fa3d417d93b56dfba37f847b": { "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": "" } }, "d3617b4b748e427e8760b3eb2cb8f793": { "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 } }, "d428517709574e439c3f6b10e0e8e0a4": { "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_d3617b4b748e427e8760b3eb2cb8f793", "placeholder": "​", "style": "IPY_MODEL_b9b0459ebe164a72b4fa1d5dc43edb43", "value": " 340/340 [00:00<00:00, 21.0kB/s]" } }, "d63e697edfa04caabc6ec3ae4b5a49e2": { "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": "" } }, "d6c4c5857d3f4e70bb45aa9dc1e4183a": { "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 } }, "d94c90d7aaae48679d7250a755174dab": { "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_91e7c57605dc4b4e8941e40aad8dcc61", "IPY_MODEL_599616631d70485bba118ddb0a6c0e6b", "IPY_MODEL_d428517709574e439c3f6b10e0e8e0a4" ], "layout": "IPY_MODEL_6371a46b268a43e1baaa091655ff3fad" } }, "de409483fac7461fabc7c67cc3a6bd07": { "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_a804df02bd1c4f6f987f20540b84c927", "placeholder": "​", "style": "IPY_MODEL_e24d137e35354ae8b62e408dd97a198e", "value": "config.json: " } }, "e24d137e35354ae8b62e408dd97a198e": { "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": "" } }, "e8648a9b28c043c4a76c4c81e207b3e0": { "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_0d3604fca4c74e2583a85d9a28e0dc28", "placeholder": "​", "style": "IPY_MODEL_8bfa67a031a7408285f7332ad6c626b4", "value": " 2.55G/2.55G [00:31<00:00, 127MB/s]" } } } } }, "nbformat": 4, "nbformat_minor": 0 }