init: working release

.gitignore

@@ -0,0 +1,116 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# input data, saved log, checkpoints
+input/
+saved/
+datasets/
+
+# editor, os cache directory
+.vscode/
+.idea/
+__MACOSX/
+
+# random imgs
+*.jpeg
+*.jpg
+*.png

README.md

@@ -0,0 +1,78 @@
+# (WIP) MakeItSports Bot Image-to-Art Search
+
+This project fine-tunes a Vision Transformer (ViT) model, pre-trained with "google/vit-base-patch32-224-in21k" weights and fine tuned with the style of [ArtButMakeItSports](https://www.instagram.com/artbutmakeitsports/), to perform image-to-art search across 81k artworks made available by [WikiArt](https://wikiart.org/).
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Installation](#installation)
+- [Usage](#usage)
+- [Dataset](#dataset)
+- [Training](#training)
+- [Inference](#inference)
+- [Contributing](#contributing)
+- [License](#license)
+
+## Overview
+
+This project leverages the Vision Transformer (ViT) model architecture for the task of image-to-art search. By fine-tuning the pre-trained ViT model on a custom dataset derived from the Instagram account [ArtButMakeItSports](https://www.instagram.com/artbutmakeitsports/), we aim to create a model capable of matching images (but not only) to corresponding artworks, being able to search for any of the images on [WikiArt](https://wikiart.org/).
+
+## Installation
+
+1. Clone the repository:
+    ```sh
+    git clone https://github.com/brunorosilva/makeitsports-bot.git
+    cd makeitsports-bot
+    ```
+
+2. Install poetry:
+    ```sh
+    pip install poetry
+    ```
+
+3. Install using poetry:
+    ```sh
+    poetry install
+    ```
+
+## How it works
+
+### Dataset Preparation
+
+1. Download images from the [ArtButMakeItSports](https://www.instagram.com/artbutmakeitsports/) Instagram account.
+2. Organize the images into appropriate directories for training and validation.
+
+### Training
+
+1. Fine-tune the ViT model:
+    ```sh
+    poetry run python main.py train --epochs 50 --batch_size 32
+    ```
+
+### Inference via Gradio
+
+1. Perform image-to-art search using the fine-tuned model:
+    ```sh
+    poetry run python main.py interface
+    ```
+
+### Create new gallery
+
+1. If you want to index new images to search, use:
+    ```sh
+    poetry run python main.py gallery --gallery_path <your_path>
+    ```
+
+## Dataset
+
+The dataset derives from 1k images from the Instagram account [ArtButMakeItSports](https://www.instagram.com/artbutmakeitsports/). Images are downloaded and split into training, validation and test sets. Each image is paired with its corresponding artwork for training purposes, if you want this dataset just ask me stating your usage.
+
+WikiArt is indexed using the same process, except that there's no expected result. So each artwork is mapped to itself and the embeddings are saved as a numpy file (will be changed to chromadb in the future).
+
+## Training
+
+The training script fine-tunes the ViT model on the prepared dataset. Key steps include:
+
+1. Loading the pre-trained "google/vit-base-patch32-224-in21k" weights.
+2. Preparing the dataset and data loaders.
+3. Fine-tuning the model using a custom training loop.

main.py

@@ -0,0 +1,48 @@
+from makeitsports_bot.models.predict import predict
+from makeitsports_bot.models.train import fine_tune_vit
+from makeitsports_bot.models.compute_embeddings import create_gallery_embeddings
+import gradio as gr
+import argparse
+
+def make_interface():
+    interface = gr.Interface(
+        fn=predict,
+        inputs=gr.Image(type="pil"),
+        outputs=gr.Gallery(label="Most similar images", height=256 * 3),
+        live=True,
+    )
+    interface.launch()
+
+def train(epochs, batch_size):
+    fine_tune_vit(epochs, batch_size)
+
+def create_gallery(gallery_path):
+    create_gallery_embeddings(gallery_path)
+
+def main():
+    parser = argparse.ArgumentParser(description="Train or infer the ViT model for image-to-art search.")
+    subparsers = parser.add_subparsers(dest="command")
+
+    # Subparser for training
+    train_parser = subparsers.add_parser("train", help="Fine-tune the ViT model")
+    train_parser.add_argument("--epochs", type=int, default=50, help="Number of training epochs")
+    train_parser.add_argument("--batch_size", type=int, default=32, help="Batch size for training")
+
+    # Subparser for inference
+    _ = subparsers.add_parser("interface", help="Perform image-to-art search using the fine-tuned model")
+
+    create_gallery_parser = subparsers.add_parser("gallery", help="Create new gallery from a path")
+    create_gallery_parser.add_argument("--gallery_path", type=str, default="data/wikiart")
+    args = parser.parse_args()
+
+    if args.command == "train":
+        train(args.epochs, args.batch_size)
+    elif args.command == "interface":
+        make_interface()
+    elif args.command == "gallery":
+        create_gallery(args.gallery_path)
+    else:
+        parser.print_help()
+
+if __name__ == "__main__":
+    main()

makeitsports_bot/constants.py

@@ -0,0 +1 @@
+BASE_PATH = "data/artmakeitsports"

makeitsports_bot/data/data.py

@@ -0,0 +1,24 @@
+from makeitsports_bot.constants import BASE_PATH
+import os
+import numpy as np
+
+
+def get_data_from_local():
+    right_data = [f"{BASE_PATH}/right/{fn}" for fn in os.listdir(f"{BASE_PATH}/right")]
+    top_data = [f"{BASE_PATH}/top/{fn}" for fn in os.listdir(f"{BASE_PATH}/top")]
+
+    x = np.array(right_data + top_data)
+    y = np.array([ex.replace("right", "left").replace("top", "bottom") for ex in x])
+
+    data = np.array([x, y])
+    return data
+
+
+def split_train_val_test(data, test_size, val_size):
+    train_size = 1 - test_size - val_size
+    SPLIT = int(data.shape[1] * train_size)
+    TEST_SPLIT = SPLIT + int(data.shape[1] * test_size)
+    train = data[:, :SPLIT]
+    validation = data[:, SPLIT:TEST_SPLIT]
+    test = data[:, TEST_SPLIT:]
+    return train, validation, test

makeitsports_bot/data/dataset.py

@@ -0,0 +1,22 @@
+from PIL import Image
+from torch.utils.data import Dataset
+
+
+class ImageRetrievalDataset(Dataset):
+    def __init__(self, data, transform=None):
+        self.data = data
+        self.transform = transform
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, idx):
+        input_path, label_path = self.data[:, idx]
+        input_image = Image.open(input_path).convert("RGB")
+        label_image = Image.open(label_path).convert("RGB")
+
+        if self.transform:
+            input_image = self.transform(input_image)
+            label_image = self.transform(label_image)
+
+        return input_image, label_image

makeitsports_bot/data/transforms.py

@@ -0,0 +1,19 @@
+from torchvision import transforms
+
+transform = transforms.Compose(
+    [
+        transforms.Resize((224, 224)),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+    ]
+)
+
+
+inversetransform = transforms.Compose(
+    [
+        transforms.Normalize(
+            mean=[0.0, 0.0, 0.0], std=[1 / 0.229, 1 / 0.224, 1 / 0.225]
+        ),
+        transforms.Normalize(mean=[-0.485, -0.456, -0.406], std=[1.0, 1.0, 1.0]),
+    ]
+)

makeitsports_bot/losses/contrastiveloss.py

@@ -0,0 +1,12 @@
+import torch
+
+
+class ContrastiveLoss(torch.nn.Module):
+    def __init__(self, margin=1.0):
+        super(ContrastiveLoss, self).__init__()
+        self.margin = margin
+
+    def forward(self, output1, output2):  # noqa
+        euclidean_distance = torch.nn.functional.pairwise_distance(output1, output2)
+        loss = torch.mean(torch.pow(euclidean_distance, 2))
+        return loss

makeitsports_bot/models/compute_embeddings.py

@@ -0,0 +1,49 @@
+import torch
+from makeitsports_bot.models.model import ViTImageSearchModel
+import numpy as np
+from sklearn.neighbors import NearestNeighbors
+from makeitsports_bot.data.dataset import ImageRetrievalDataset
+from makeitsports_bot.data.transforms import transform
+from tqdm import tqdm
+import os
+
+def extract_embedding(image_data, fine_tuned_model):
+    image = image_data.unsqueeze(0)
+    with torch.no_grad():
+        embedding = fine_tuned_model(image).cpu().numpy()
+    return embedding
+
+
+def load_fine_tuned_model():
+    fine_tuned_model = ViTImageSearchModel()
+    fine_tuned_model.load_state_dict(torch.load("results/model.pth"))
+    fine_tuned_model.eval()
+    return fine_tuned_model
+
+
+def create_gallery(dataset, fine_tuned_model, save=True):
+    gallery_embeddings = []
+    for img_path, _ in tqdm(dataset):
+        embedding = extract_embedding(img_path, fine_tuned_model)
+        gallery_embeddings.append(embedding)
+    gallery_embeddings = np.vstack(gallery_embeddings)
+    if save:
+        np.save("results/embeddings", gallery_embeddings)
+    return gallery_embeddings
+
+
+def search_image(query_image_path, gallery_embeddings, k=4):
+    fine_tuned_model = load_fine_tuned_model()
+    query_embedding = extract_embedding(query_image_path, fine_tuned_model)
+    neighbors = NearestNeighbors(n_neighbors=k, metric="euclidean")
+    neighbors.fit(gallery_embeddings)
+    distances, indices = neighbors.kneighbors(query_embedding)
+    return indices, distances
+
+
+def create_gallery_embeddings(folder):  # noqa
+    x = np.array([f"{folder}/{file}" for file in os.listdir(folder)])
+    gallery_data = np.array([x, x])
+    gallery_dataset = ImageRetrievalDataset(gallery_data, transform=transform)
+    fine_tuned_model = load_fine_tuned_model()
+    create_gallery(gallery_dataset, fine_tuned_model)

makeitsports_bot/models/model.py

@@ -0,0 +1,13 @@
+from transformers import ViTModel
+from torch import nn
+
+
+class ViTImageSearchModel(nn.Module):
+    def __init__(self, pretrained_model_name="google/vit-base-patch32-224-in21k"):
+        super(ViTImageSearchModel, self).__init__()
+        self.vit = ViTModel.from_pretrained(pretrained_model_name)
+
+    def forward(self, x):  # noqa
+        outputs = self.vit(pixel_values=x)
+        cls_hidden_state = outputs.last_hidden_state[:, 0, :]
+        return cls_hidden_state

makeitsports_bot/models/predict.py

@@ -0,0 +1,29 @@
+from makeitsports_bot.data.dataset import ImageRetrievalDataset
+from makeitsports_bot.data.transforms import transform
+from makeitsports_bot.models.train import fine_tune_vit
+from makeitsports_bot.utils import inverse_transform_img
+from makeitsports_bot.models.compute_embeddings import (
+    search_image,
+    create_gallery,
+    load_fine_tuned_model,
+)
+import numpy as np
+import os
+from PIL import Image
+
+
+def predict(img: Image):
+    x = np.array([f"data/wikiart/{file}" for file in os.listdir("data/wikiart")])
+    wikiart_data = np.array([x, x])
+    wikiart_dataset = ImageRetrievalDataset(wikiart_data, transform=transform)
+    gallery_embeddings = np.load("results/embeddings.npy")
+    tmp_img_path = "tmp_img.png"
+    img.save(tmp_img_path)
+    pred_img = np.array([[tmp_img_path], [tmp_img_path]])
+    pred_dataset = ImageRetrievalDataset(pred_img, transform=transform)
+    indices, distances = search_image(pred_dataset[0][0], gallery_embeddings)
+    results = []
+    for idx, _ in zip(indices[0], distances[0]):
+        inv_tensor = inverse_transform_img(wikiart_dataset[idx][1]).cpu().numpy()
+        results.append(inv_tensor)
+    return results

makeitsports_bot/models/train.py

@@ -0,0 +1,74 @@
+from makeitsports_bot.data.dataset import ImageRetrievalDataset
+from torch.utils.data import DataLoader
+from makeitsports_bot.losses.contrastiveloss import ContrastiveLoss
+from makeitsports_bot.data.data import get_data_from_local, split_train_val_test
+from makeitsports_bot.data.transforms import transform
+from makeitsports_bot.models.model import ViTImageSearchModel
+import torch
+from torch.optim import Adam
+from torch.utils.tensorboard import SummaryWriter
+import numpy as np
+
+
+def fine_tune_vit(epochs, batch_size):
+    data = get_data_from_local()
+    train_data, val_data, test_data = split_train_val_test(data, 0.2, 0.1)
+    np.save("results/test_data", test_data)
+    train_dataset = ImageRetrievalDataset(train_data, transform=transform)
+    val_dataset = ImageRetrievalDataset(val_data, transform=transform)
+
+    train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
+    val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)
+
+    model = ViTImageSearchModel()
+
+    # logs
+    log_dir = "./logs/"
+    writer = SummaryWriter(log_dir=log_dir)
+
+    # params
+    criterion = ContrastiveLoss()
+    optimizer = Adam(model.parameters(), lr=1e-4)
+    epochs = epochs
+
+    for epoch in range(epochs):
+        model.train()
+        total_loss = 0
+
+        for batch_idx, batch in enumerate(train_loader):
+            inputs, labels = batch
+            optimizer.zero_grad()
+
+            input_embeddings = model(inputs)
+            label_embeddings = model(labels)
+
+            loss = criterion(input_embeddings, label_embeddings)
+
+            loss.backward()
+            optimizer.step()
+
+            total_loss += loss.item()
+            writer.add_scalar(
+                "Train Loss", loss.item(), epoch * len(train_loader) + batch_idx
+            )
+
+        avg_train_loss = total_loss / len(train_loader)
+        writer.add_scalar("Average Train Loss", avg_train_loss, epoch)
+
+        print(f"Epoch [{epoch+1}/{epochs}], Loss: {total_loss/len(train_loader)}")
+
+        model.eval()
+        with torch.no_grad():
+            val_loss = 0
+            for batch_idx, batch in enumerate(val_loader):
+                inputs, labels = batch
+                input_embeddings = model(inputs)
+                label_embeddings = model(labels)
+
+                loss = criterion(input_embeddings, label_embeddings)
+                val_loss += loss.item()
+            avg_val_loss = val_loss / len(val_loader)
+            writer.add_scalar("Validation Loss", avg_val_loss, epoch)
+            print(f"Validation Loss: {val_loss/len(val_loader)}")
+
+    torch.save(model.state_dict(), "results/model.pth")

makeitsports_bot/utils.py

@@ -0,0 +1,6 @@
+from makeitsports_bot.data.transforms import inversetransform
+
+
+def inverse_transform_img(img):
+    inv_tensor = inversetransform(img)
+    return inv_tensor.permute(1, 2, 0)

notebooks/0-0-brsc-create-dataset.ipynb

@@ -0,0 +1,399 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f5c16e68-e20a-473c-9d0c-557314b32203",
+   "metadata": {},
+   "source": [
+    "## Creating the dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "f4e1aece-855e-4687-81d4-376da67545e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "fadf8ef6-ab1c-46a7-962c-512b61cff8b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_path = \"../data/artmakeitsports/\"\n",
+    "folders = [f'{base_path}{file}' for file in os.listdir(base_path)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "99514288-bb6c-4b62-bf0e-f66c86b246b2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['../data/artmakeitsports/right',\n",
+       " '../data/artmakeitsports/top',\n",
+       " '../data/artmakeitsports/bruno.jpg',\n",
+       " '../data/artmakeitsports/image_test.jpeg',\n",
+       " '../data/artmakeitsports/train',\n",
+       " '../data/artmakeitsports/t.jpg',\n",
+       " '../data/artmakeitsports/bruno.jpeg',\n",
+       " '../data/artmakeitsports/validation',\n",
+       " '../data/artmakeitsports/left',\n",
+       " '../data/artmakeitsports/hugo.jpeg',\n",
+       " '../data/artmakeitsports/datasets',\n",
+       " '../data/artmakeitsports/bottom']"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "folders"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e3b1185-7fa1-4eb5-996f-415fce3f1cf1",
+   "metadata": {},
+   "source": [
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "5c0519e8-bbfd-4f6b-ba4a-ae099de57598",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "9de6eb5e-0144-45e9-9eb0-faad01a94b66",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = np.array([])\n",
+    "for folder in [\"../data/artmakeitsports/right\", \"../data/artmakeitsports/top\"]:\n",
+    "    x = np.append(x, np.array([f\"{folder}/{file}\" for file in os.listdir(folder)]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "f0b773aa-8a55-4fdf-926a-b822e8941526",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/usr/bin/zsh: /home/rosilva/miniconda3/envs/lori/lib/libtinfo.so.6: no version information available (required by /usr/bin/zsh)\n",
+      "bottom\t    bruno.jpg  hugo.jpeg\tleft   t.jpg  train\n",
+      "bruno.jpeg  datasets   image_test.jpeg\tright  top    validation\n"
+     ]
+    }
+   ],
+   "source": [
+    "!ls ../data/artmakeitsports/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "b5fde846-d0ac-44f6-83e6-daa74aced018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "hugo = [\"../data/artmakeitsports/image_test.jpeg\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "1f03d876-ed34-4465-961b-b2411aadf35f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "hugo = np.array([hugo, hugo])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "4b28832b-fee1-4b6b-a8cc-773c8cab4219",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([['../data/artmakeitsports/image_test.jpeg'],\n",
+       "       ['../data/artmakeitsports/image_test.jpeg']], dtype='<U39')"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "hugo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "de89352d-6c8c-48ba-a255-f2362d8b8a56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.save(\"hugo\", hugo)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "a219c737-049a-4dc1-9c56-0def8236139d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(663,)"
+      ]
+     },
+     "execution_count": 87,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "id": "dde185c5-e754-4683-8f00-85311639249f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = np.array([ex.replace(\"right\", \"left\").replace(\"top\", \"bottom\") for ex in x])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "id": "47c27bef-e6d5-426c-9788-0b06ce6096e1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(663,)"
+      ]
+     },
+     "execution_count": 89,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "id": "5068a082-b787-4cd7-a973-c91bbcba33e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = np.array([x, y])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "id": "a8b81faf-1459-4549-9411-22951667c6c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "663"
+      ]
+     },
+     "execution_count": 91,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset.shape[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "id": "a599869f-d33f-4a7b-8772-1f2fdf50555d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "SPLIT = int(dataset.shape[1]*.8)\n",
+    "TEST_SPLIT = SPLIT + int(dataset.shape[1]*.1)\n",
+    "train = dataset[:,:SPLIT]\n",
+    "validation = dataset[:,SPLIT:TEST_SPLIT]\n",
+    "test = dataset[:,TEST_SPLIT:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "id": "e41f40ad-0da6-43eb-b2c2-1f24283063b7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2, 530)"
+      ]
+     },
+     "execution_count": 93,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "id": "28d94611-15a0-4f9b-8920-b6765572125c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2, 66)"
+      ]
+     },
+     "execution_count": 94,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "validation.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "aea0f3c6-ed5f-4f9a-97e9-1b4bbadae359",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2, 67)"
+      ]
+     },
+     "execution_count": 95,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "af13d764-0730-4afe-9711-5cd16035337d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'../data/artmakeitsports/'"
+      ]
+     },
+     "execution_count": 96,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "base_path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "id": "b9a7971d-aa5d-4d08-9531-7596475fbc04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.mkdir(f\"{base_path}datasets\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "id": "543b504e-1646-4c80-8e74-f42dc6251f66",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.save(f\"{base_path}datasets/train\", train)\n",
+    "np.save(f\"{base_path}datasets/validation\", validation)\n",
+    "np.save(f\"{base_path}datasets/test\", test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17b6829d-2c2b-4635-8301-9c2c6e738446",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/0-2-brsc-create-wikiart-dataset.ipynb

@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f5c16e68-e20a-473c-9d0c-557314b32203",
+   "metadata": {},
+   "source": [
+    "## Creating the dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f4e1aece-855e-4687-81d4-376da67545e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5c0519e8-bbfd-4f6b-ba4a-ae099de57598",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fadf8ef6-ab1c-46a7-962c-512b61cff8b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_path = \"../data/wikiart/\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9de6eb5e-0144-45e9-9eb0-faad01a94b66",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = np.array([])\n",
+    "x = np.append(x, np.array([f\"{base_path}{file}\" for file in os.listdir(base_path)]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "5d787870-a55e-4322-8df6-bd7b7e3f48da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(80082,)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b5fde846-d0ac-44f6-83e6-daa74aced018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wikiart_dataset = np.array([x, x])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f9ab90a1-e78f-4009-9d97-e0a7066c36c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2, 80082)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wikiart_dataset.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "de89352d-6c8c-48ba-a255-f2362d8b8a56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.save(\"../data/artmakeitsports/datasets/wikiart_data\", wikiart_dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17b6829d-2c2b-4635-8301-9c2c6e738446",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

poetry.lock

@@ -0,0 +1,1745 @@
+[[package]]
+name = "absl-py"
+version = "2.1.0"
+description = "Abseil Python Common Libraries, see https://github.com/abseil/abseil-py."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "aiofiles"
+version = "23.2.1"
+description = "File support for asyncio."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "altair"
+version = "5.3.0"
+description = "Vega-Altair: A declarative statistical visualization library for Python."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+jinja2 = "*"
+jsonschema = ">=3.0"
+numpy = "*"
+packaging = "*"
+pandas = ">=0.25"
+toolz = "*"
+typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+all = ["altair-tiles (>=0.3.0)", "anywidget (>=0.9.0)", "pyarrow (>=11)", "vega-datasets (>=0.9.0)", "vegafusion[embed] (>=1.6.6)", "vl-convert-python (>=1.3.0)"]
+dev = ["geopandas", "hatch", "ipython", "m2r", "mypy", "pandas-stubs", "pytest", "pytest-cov", "ruff (>=0.3.0)", "types-jsonschema", "types-setuptools"]
+doc = ["docutils", "jinja2", "myst-parser", "numpydoc", "pillow (>=9,<10)", "pydata-sphinx-theme (>=0.14.1)", "scipy", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinxext-altair"]
+
+[[package]]
+name = "annotated-types"
+version = "0.7.0"
+description = "Reusable constraint types to use with typing.Annotated"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "anyio"
+version = "4.4.0"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
+idna = ">=2.8"
+sniffio = ">=1.1"
+typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+doc = ["packaging", "Sphinx (>=7)", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
+test = ["anyio", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
+trio = ["trio (>=0.23)"]
+
+[[package]]
+name = "attrs"
+version = "23.2.0"
+description = "Classes Without Boilerplate"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+cov = ["attrs", "coverage[toml] (>=5.3)"]
+dev = ["attrs", "pre-commit"]
+docs = ["furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier", "zope-interface"]
+tests = ["attrs", "zope-interface"]
+tests-mypy = ["mypy (>=1.6)", "pytest-mypy-plugins"]
+tests-no-zope = ["attrs", "cloudpickle", "hypothesis", "pympler", "pytest-xdist", "pytest (>=4.3.0)"]
+
+[[package]]
+name = "black"
+version = "24.4.2"
+description = "The uncompromising code formatter."
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+click = ">=8.0.0"
+mypy-extensions = ">=0.4.3"
+packaging = ">=22.0"
+pathspec = ">=0.9.0"
+platformdirs = ">=2"
+tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
+typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+colorama = ["colorama (>=0.4.3)"]
+d = ["aiohttp (>=3.7.4,!=3.9.0)", "aiohttp (>=3.7.4)"]
+jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
+uvloop = ["uvloop (>=0.15.2)"]
+
+[[package]]
+name = "certifi"
+version = "2024.6.2"
+description = "Python package for providing Mozilla's CA Bundle."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "charset-normalizer"
+version = "3.3.2"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+
+[[package]]
+name = "click"
+version = "8.1.7"
+description = "Composable command line interface toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+
+[[package]]
+name = "contourpy"
+version = "1.2.1"
+description = "Python library for calculating contours of 2D quadrilateral grids"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[package.dependencies]
+numpy = ">=1.20"
+
+[package.extras]
+docs = ["furo", "sphinx (>=7.2)", "sphinx-copybutton"]
+bokeh = ["bokeh", "selenium"]
+mypy = ["contourpy", "docutils-stubs", "mypy (==1.8.0)", "types-pillow"]
+test = ["contourpy", "matplotlib", "pillow"]
+test-no-images = ["pytest", "pytest-cov", "pytest-xdist", "wurlitzer"]
+
+[[package]]
+name = "cycler"
+version = "0.12.1"
+description = "Composable style cycles"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["ipython", "matplotlib", "numpydoc", "sphinx"]
+tests = ["pytest", "pytest-cov", "pytest-xdist"]
+
+[[package]]
+name = "dnspython"
+version = "2.6.1"
+description = "DNS toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+dev = ["black (>=23.1.0)", "coverage (>=7.0)", "flake8 (>=7)", "mypy (>=1.8)", "pylint (>=3)", "pytest-cov (>=4.1.0)", "pytest (>=7.4)", "sphinx (>=7.2.0)", "twine (>=4.0.0)", "wheel (>=0.42.0)"]
+dnssec = ["cryptography (>=41)"]
+doh = ["h2 (>=4.1.0)", "httpcore (>=1.0.0)", "httpx (>=0.26.0)"]
+doq = ["aioquic (>=0.9.25)"]
+idna = ["idna (>=3.6)"]
+trio = ["trio (>=0.23)"]
+wmi = ["wmi (>=1.5.1)"]
+
+[[package]]
+name = "email-validator"
+version = "2.2.0"
+description = "A robust email address syntax and deliverability validation library."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+dnspython = ">=2.0.0"
+idna = ">=2.0.0"
+
+[[package]]
+name = "exceptiongroup"
+version = "1.2.1"
+description = "Backport of PEP 654 (exception groups)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
+name = "fastapi"
+version = "0.111.0"
+description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+email_validator = ">=2.0.0"
+fastapi-cli = ">=0.0.2"
+httpx = ">=0.23.0"
+jinja2 = ">=2.11.2"
+orjson = ">=3.2.1"
+pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.1.0 || >2.1.0,<3.0.0"
+python-multipart = ">=0.0.7"
+starlette = ">=0.37.2,<0.38.0"
+typing-extensions = ">=4.8.0"
+ujson = ">=4.0.1,<4.0.2 || >4.0.2,<4.1.0 || >4.1.0,<4.2.0 || >4.2.0,<4.3.0 || >4.3.0,<5.0.0 || >5.0.0,<5.1.0 || >5.1.0"
+uvicorn = {version = ">=0.12.0", extras = ["standard"]}
+
+[package.extras]
+all = ["httpx (>=0.23.0)", "jinja2 (>=2.11.2)", "python-multipart (>=0.0.7)", "itsdangerous (>=1.1.0)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "orjson (>=3.2.1)", "email_validator (>=2.0.0)", "uvicorn[standard] (>=0.12.0)", "pydantic-settings (>=2.0.0)", "pydantic-extra-types (>=2.0.0)"]
+
+[[package]]
+name = "fastapi-cli"
+version = "0.0.4"
+description = "Run and manage FastAPI apps from the command line with FastAPI CLI. 🚀"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+typer = ">=0.12.3"
+
+[package.extras]
+standard = ["fastapi", "uvicorn[standard] (>=0.15.0)"]
+
+[[package]]
+name = "ffmpy"
+version = "0.3.2"
+description = "A simple Python wrapper for ffmpeg"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "filelock"
+version = "3.15.4"
+description = "A platform independent file lock."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["furo (>=2023.9.10)", "sphinx-autodoc-typehints (>=1.25.2)", "sphinx (>=7.2.6)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest-asyncio (>=0.21)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)", "pytest (>=7.4.3)", "virtualenv (>=20.26.2)"]
+typing = ["typing-extensions (>=4.8)"]
+
+[[package]]
+name = "flake8"
+version = "7.1.0"
+description = "the modular source code checker: pep8 pyflakes and co"
+category = "dev"
+optional = false
+python-versions = ">=3.8.1"
+
+[package.dependencies]
+mccabe = ">=0.7.0,<0.8.0"
+pycodestyle = ">=2.12.0,<2.13.0"
+pyflakes = ">=3.2.0,<3.3.0"
+
+[[package]]
+name = "fonttools"
+version = "4.53.0"
+description = "Tools to manipulate font files"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+all = ["fs (>=2.2.0,<3)", "lxml (>=4.0)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "pycairo", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "uharfbuzz (>=0.23.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=15.1.0)", "xattr"]
+graphite = ["lz4 (>=1.7.4.2)"]
+interpolatable = ["pycairo", "scipy", "munkres"]
+lxml = ["lxml (>=4.0)"]
+pathops = ["skia-pathops (>=0.5.0)"]
+plot = ["matplotlib"]
+repacker = ["uharfbuzz (>=0.23.0)"]
+symfont = ["sympy"]
+type1 = ["xattr"]
+ufo = ["fs (>=2.2.0,<3)"]
+unicode = ["unicodedata2 (>=15.1.0)"]
+woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
+
+[[package]]
+name = "fsspec"
+version = "2024.6.1"
+description = "File-system specification"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+dev = ["pre-commit", "ruff"]
+doc = ["numpydoc", "sphinx", "sphinx-design", "sphinx-rtd-theme", "yarl"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"]
+test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask-expr", "dask", "moto[server] (>4,<5)", "pytest-timeout", "xarray"]
+test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"]
+tqdm = ["tqdm"]
+
+[[package]]
+name = "gradio"
+version = "4.37.2"
+description = "Python library for easily interacting with trained machine learning models"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+aiofiles = ">=22.0,<24.0"
+altair = ">=4.2.0,<6.0"
+fastapi = "*"
+ffmpy = "*"
+gradio-client = "1.0.2"
+httpx = ">=0.24.1"
+huggingface-hub = ">=0.19.3"
+importlib-resources = ">=1.3,<7.0"
+jinja2 = "<4.0"
+markupsafe = ">=2.0,<3.0"
+matplotlib = ">=3.0,<4.0"
+numpy = ">=1.0,<3.0"
+orjson = ">=3.0,<4.0"
+packaging = "*"
+pandas = ">=1.0,<3.0"
+pillow = ">=8.0,<11.0"
+pydantic = ">=2.0"
+pydub = "*"
+python-multipart = ">=0.0.9"
+pyyaml = ">=5.0,<7.0"
+ruff = {version = ">=0.2.2", markers = "sys_platform != \"emscripten\""}
+semantic-version = ">=2.0,<3.0"
+tomlkit = "0.12.0"
+typer = {version = ">=0.12,<1.0", markers = "sys_platform != \"emscripten\""}
+typing-extensions = ">=4.0,<5.0"
+urllib3 = ">=2.0,<3.0"
+uvicorn = {version = ">=0.14.0", markers = "sys_platform != \"emscripten\""}
+
+[package.extras]
+oauth = ["authlib", "itsdangerous"]
+
+[[package]]
+name = "gradio-client"
+version = "1.0.2"
+description = "Python library for easily interacting with trained machine learning models"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+fsspec = "*"
+httpx = ">=0.24.1"
+huggingface-hub = ">=0.19.3"
+packaging = "*"
+typing-extensions = ">=4.0,<5.0"
+websockets = ">=10.0,<12.0"
+
+[[package]]
+name = "grpcio"
+version = "1.64.1"
+description = "HTTP/2-based RPC framework"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+protobuf = ["grpcio-tools (>=1.64.1)"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "httpcore"
+version = "1.0.5"
+description = "A minimal low-level HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+certifi = "*"
+h11 = ">=0.13,<0.15"
+
+[package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+trio = ["trio (>=0.22.0,<0.26.0)"]
+
+[[package]]
+name = "httptools"
+version = "0.6.1"
+description = "A collection of framework independent HTTP protocol utils."
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+
+[package.extras]
+test = ["Cython (>=0.29.24,<0.30.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.27.0"
+description = "The next generation HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = ">=1.0.0,<2.0.0"
+idna = "*"
+sniffio = "*"
+
+[package.extras]
+brotli = ["brotli", "brotlicffi"]
+cli = ["click (>=8.0.0,<9.0.0)", "pygments (>=2.0.0,<3.0.0)", "rich (>=10,<14)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+
+[[package]]
+name = "huggingface-hub"
+version = "0.23.4"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+
+[package.dependencies]
+filelock = "*"
+fsspec = ">=2023.5.0"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "aiohttp", "minijinja (>=1.0)", "jedi", "jinja2", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "pytest-vcr", "pytest-asyncio", "pytest-rerunfailures", "urllib3 (<2.0)", "soundfile", "pillow", "gradio", "numpy", "fastapi", "ruff (>=0.3.0)", "mypy (==1.5.1)", "typing-extensions (>=4.8.0)", "types-pyyaml", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "aiohttp", "minijinja (>=1.0)", "jedi", "jinja2", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "pytest-vcr", "pytest-asyncio", "pytest-rerunfailures", "urllib3 (<2.0)", "soundfile", "pillow", "gradio", "numpy", "fastapi", "ruff (>=0.3.0)", "mypy (==1.5.1)", "typing-extensions (>=4.8.0)", "types-pyyaml", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+fastai = ["toml", "fastai (>=2.4)", "fastcore (>=1.3.27)"]
+hf-transfer = ["hf-transfer (>=0.1.4)"]
+inference = ["aiohttp", "minijinja (>=1.0)"]
+quality = ["ruff (>=0.3.0)", "mypy (==1.5.1)"]
+tensorflow = ["tensorflow", "pydot", "graphviz"]
+tensorflow-testing = ["tensorflow", "keras (<3.0)"]
+testing = ["InquirerPy (==0.3.4)", "aiohttp", "minijinja (>=1.0)", "jedi", "jinja2", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "pytest-vcr", "pytest-asyncio", "pytest-rerunfailures", "urllib3 (<2.0)", "soundfile", "pillow", "gradio", "numpy", "fastapi"]
+torch = ["torch", "safetensors"]
+typing = ["typing-extensions (>=4.8.0)", "types-pyyaml", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+
+[[package]]
+name = "idna"
+version = "3.7"
+description = "Internationalized Domain Names in Applications (IDNA)"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "importlib-resources"
+version = "6.4.0"
+description = "Read resources from Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["sphinx (>=3.5)", "sphinx (<7.2.5)", "jaraco.packaging (>=9.3)", "rst.linker (>=1.9)", "furo", "sphinx-lint", "jaraco.tidelift (>=1.4)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ruff (>=0.2.1)", "zipp (>=3.17)", "jaraco.test (>=5.4)", "pytest-mypy"]
+
+[[package]]
+name = "intel-openmp"
+version = "2021.4.0"
+description = "Intel OpenMP* Runtime Library"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "jinja2"
+version = "3.1.4"
+description = "A very fast and expressive template engine."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "joblib"
+version = "1.4.2"
+description = "Lightweight pipelining with Python functions"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "jsonschema"
+version = "4.22.0"
+description = "An implementation of JSON Schema validation for Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+attrs = ">=22.2.0"
+jsonschema-specifications = ">=2023.03.6"
+referencing = ">=0.28.4"
+rpds-py = ">=0.7.1"
+
+[package.extras]
+format = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3987", "uri-template", "webcolors (>=1.11)"]
+format-nongpl = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "uri-template", "webcolors (>=1.11)"]
+
+[[package]]
+name = "jsonschema-specifications"
+version = "2023.12.1"
+description = "The JSON Schema meta-schemas and vocabularies, exposed as a Registry"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+referencing = ">=0.31.0"
+
+[[package]]
+name = "kiwisolver"
+version = "1.4.5"
+description = "A fast implementation of the Cassowary constraint solver"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "markdown"
+version = "3.6"
+description = "Python implementation of John Gruber's Markdown."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["mkdocs (>=1.5)", "mkdocs-nature (>=0.6)", "mdx-gh-links (>=0.2)", "mkdocstrings", "mkdocs-gen-files", "mkdocs-section-index", "mkdocs-literate-nav"]
+testing = ["coverage", "pyyaml"]
+
+[[package]]
+name = "markdown-it-py"
+version = "3.0.0"
+description = "Python port of markdown-it. Markdown parsing, done right!"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+mdurl = ">=0.1,<1.0"
+
+[package.extras]
+benchmarking = ["psutil", "pytest", "pytest-benchmark"]
+code_style = ["pre-commit (>=3.0,<4.0)"]
+compare = ["commonmark (>=0.9,<1.0)", "markdown (>=3.4,<4.0)", "mistletoe (>=1.0,<2.0)", "mistune (>=2.0,<3.0)", "panflute (>=2.3,<3.0)"]
+linkify = ["linkify-it-py (>=1,<3)"]
+plugins = ["mdit-py-plugins"]
+profiling = ["gprof2dot"]
+rtd = ["mdit-py-plugins", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx-book-theme", "jupyter-sphinx"]
+testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.5"
+description = "Safely add untrusted strings to HTML/XML markup."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "matplotlib"
+version = "3.9.0"
+description = "Python plotting package"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[package.dependencies]
+contourpy = ">=1.0.1"
+cycler = ">=0.10"
+fonttools = ">=4.22.0"
+kiwisolver = ">=1.3.1"
+numpy = ">=1.23"
+packaging = ">=20.0"
+pillow = ">=8"
+pyparsing = ">=2.3.1"
+python-dateutil = ">=2.7"
+
+[package.extras]
+dev = ["meson-python (>=0.13.1)", "numpy (>=1.25)", "pybind11 (>=2.6)", "setuptools_scm (>=7)", "setuptools (>=64)"]
+
+[[package]]
+name = "mccabe"
+version = "0.7.0"
+description = "McCabe checker, plugin for flake8"
+category = "dev"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "mdurl"
+version = "0.1.2"
+description = "Markdown URL utilities"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "mkl"
+version = "2021.4.0"
+description = "Intel® oneAPI Math Kernel Library"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+intel-openmp = ">=2021.0.0,<2022.0.0"
+tbb = ">=2021.0.0,<2022.0.0"
+
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.extras]
+develop = ["pytest (>=4.6)", "pycodestyle", "pytest-cov", "codecov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
+[[package]]
+name = "mypy"
+version = "1.10.1"
+description = "Optional static typing for Python"
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+mypy-extensions = ">=1.0.0"
+tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
+typing-extensions = ">=4.1.0"
+
+[package.extras]
+dmypy = ["psutil (>=4.0)"]
+install-types = ["pip"]
+mypyc = ["setuptools (>=50)"]
+reports = ["lxml"]
+
+[[package]]
+name = "mypy-extensions"
+version = "1.0.0"
+description = "Type system extensions for programs checked with the mypy type checker."
+category = "dev"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "networkx"
+version = "3.3"
+description = "Python package for creating and manipulating graphs and networks"
+category = "main"
+optional = false
+python-versions = ">=3.10"
+
+[package.extras]
+default = ["numpy (>=1.23)", "scipy (>=1.9,!=1.11.0,!=1.11.1)", "matplotlib (>=3.6)", "pandas (>=1.4)"]
+developer = ["changelist (==0.5)", "pre-commit (>=3.2)", "mypy (>=1.1)", "rtoml"]
+doc = ["sphinx (>=7)", "pydata-sphinx-theme (>=0.14)", "sphinx-gallery (>=0.14)", "numpydoc (>=1.7)", "pillow (>=9.4)", "texext (>=0.6.7)", "myst-nb (>=1.0)"]
+extra = ["lxml (>=4.6)", "pygraphviz (>=1.12)", "pydot (>=2.0)", "sympy (>=1.10)"]
+test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
+[[package]]
+name = "numpy"
+version = "2.0.0"
+description = "Fundamental package for array computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+description = "CUBLAS native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.1.105"
+description = "CUDA profiling tools runtime libs."
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.1.105"
+description = "NVRTC native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.1.105"
+description = "CUDA Runtime native Libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "8.9.2.26"
+description = "cuDNN runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+description = "CUFFT native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.2.106"
+description = "CURAND native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.4.5.107"
+description = "CUDA solver native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+nvidia-cusparse-cu12 = "*"
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+description = "CUSPARSE native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.20.5"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.5.40"
+description = "Nvidia JIT LTO Library"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.1.105"
+description = "NVIDIA Tools Extension"
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "orjson"
+version = "3.10.5"
+description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "packaging"
+version = "24.1"
+description = "Core utilities for Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "pandas"
+version = "2.2.2"
+description = "Powerful data structures for data analysis, time series, and statistics"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[package.dependencies]
+numpy = [
+    {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+]
+python-dateutil = ">=2.8.2"
+pytz = ">=2020.1"
+tzdata = ">=2022.7"
+
+[package.extras]
+test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"]
+pyarrow = ["pyarrow (>=10.0.1)"]
+performance = ["bottleneck (>=1.3.6)", "numba (>=0.56.4)", "numexpr (>=2.8.4)"]
+computation = ["scipy (>=1.10.0)", "xarray (>=2022.12.0)"]
+fss = ["fsspec (>=2022.11.0)"]
+aws = ["s3fs (>=2022.11.0)"]
+gcp = ["gcsfs (>=2022.11.0)", "pandas-gbq (>=0.19.0)"]
+excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)"]
+parquet = ["pyarrow (>=10.0.1)"]
+feather = ["pyarrow (>=10.0.1)"]
+hdf5 = ["tables (>=3.8.0)"]
+spss = ["pyreadstat (>=1.2.0)"]
+postgresql = ["SQLAlchemy (>=2.0.0)", "psycopg2 (>=2.9.6)", "adbc-driver-postgresql (>=0.8.0)"]
+mysql = ["SQLAlchemy (>=2.0.0)", "pymysql (>=1.0.2)"]
+sql-other = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)"]
+html = ["beautifulsoup4 (>=4.11.2)", "html5lib (>=1.1)", "lxml (>=4.9.2)"]
+xml = ["lxml (>=4.9.2)"]
+plot = ["matplotlib (>=3.6.3)"]
+output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.9.0)"]
+clipboard = ["PyQt5 (>=5.15.9)", "qtpy (>=2.3.0)"]
+compression = ["zstandard (>=0.19.0)"]
+consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
+all = ["adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)", "beautifulsoup4 (>=4.11.2)", "bottleneck (>=1.3.6)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=2022.12.0)", "fsspec (>=2022.11.0)", "gcsfs (>=2022.11.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.9.2)", "matplotlib (>=3.6.3)", "numba (>=0.56.4)", "numexpr (>=2.8.4)", "odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "pandas-gbq (>=0.19.0)", "psycopg2 (>=2.9.6)", "pyarrow (>=10.0.1)", "pymysql (>=1.0.2)", "PyQt5 (>=5.15.9)", "pyreadstat (>=1.2.0)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "qtpy (>=2.3.0)", "scipy (>=1.10.0)", "s3fs (>=2022.11.0)", "SQLAlchemy (>=2.0.0)", "tables (>=3.8.0)", "tabulate (>=0.9.0)", "xarray (>=2022.12.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)", "zstandard (>=0.19.0)"]
+
+[[package]]
+name = "pathspec"
+version = "0.12.1"
+description = "Utility library for gitignore style pattern matching of file paths."
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "pillow"
+version = "10.3.0"
+description = "Python Imaging Library (Fork)"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["furo", "olefile", "sphinx (>=2.4)", "sphinx-copybutton", "sphinx-inline-tabs", "sphinx-removed-in", "sphinxext-opengraph"]
+fpx = ["olefile"]
+mic = ["olefile"]
+tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
+typing = ["typing-extensions"]
+xmp = ["defusedxml"]
+
+[[package]]
+name = "platformdirs"
+version = "4.2.2"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+docs = ["furo (>=2023.9.10)", "proselint (>=0.13)", "sphinx-autodoc-typehints (>=1.25.2)", "sphinx (>=7.2.6)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest (>=7.4.3)"]
+type = ["mypy (>=1.8)"]
+
+[[package]]
+name = "protobuf"
+version = "4.25.3"
+description = ""
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "pycodestyle"
+version = "2.12.0"
+description = "Python style guide checker"
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "pydantic"
+version = "2.7.4"
+description = "Data validation using Python type hints"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+annotated-types = ">=0.4.0"
+pydantic-core = "2.18.4"
+typing-extensions = ">=4.6.1"
+
+[package.extras]
+email = ["email-validator (>=2.0.0)"]
+
+[[package]]
+name = "pydantic-core"
+version = "2.18.4"
+description = "Core functionality for Pydantic validation and serialization"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
+
+[[package]]
+name = "pydub"
+version = "0.25.1"
+description = "Manipulate audio with an simple and easy high level interface"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pyflakes"
+version = "3.2.0"
+description = "passive checker of Python programs"
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "pygments"
+version = "2.18.0"
+description = "Pygments is a syntax highlighting package written in Python."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+windows-terminal = ["colorama (>=0.4.6)"]
+
+[[package]]
+name = "pyparsing"
+version = "3.1.2"
+description = "pyparsing module - Classes and methods to define and execute parsing grammars"
+category = "main"
+optional = false
+python-versions = ">=3.6.8"
+
+[package.extras]
+diagrams = ["railroad-diagrams", "jinja2"]
+
+[[package]]
+name = "python-dateutil"
+version = "2.9.0.post0"
+description = "Extensions to the standard Python datetime module"
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+
+[package.dependencies]
+six = ">=1.5"
+
+[[package]]
+name = "python-dotenv"
+version = "1.0.1"
+description = "Read key-value pairs from a .env file and set them as environment variables"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+cli = ["click (>=5.0)"]
+
+[[package]]
+name = "python-multipart"
+version = "0.0.9"
+description = "A streaming multipart parser for Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+dev = ["atomicwrites (==1.4.1)", "attrs (==23.2.0)", "coverage (==7.4.1)", "hatch", "invoke (==2.2.0)", "more-itertools (==10.2.0)", "pbr (==6.0.0)", "pluggy (==1.4.0)", "py (==1.11.0)", "pytest-cov (==4.1.0)", "pytest-timeout (==2.2.0)", "pytest (==8.0.0)", "pyyaml (==6.0.1)", "ruff (==0.2.1)"]
+
+[[package]]
+name = "pytz"
+version = "2024.1"
+description = "World timezone definitions, modern and historical"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pyyaml"
+version = "6.0.1"
+description = "YAML parser and emitter for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "referencing"
+version = "0.35.1"
+description = "JSON Referencing + Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+attrs = ">=22.2.0"
+rpds-py = ">=0.7.0"
+
+[[package]]
+name = "regex"
+version = "2024.5.15"
+description = "Alternative regular expression module, to replace re."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "requests"
+version = "2.32.3"
+description = "Python HTTP for Humans."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "rich"
+version = "13.7.1"
+description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+
+[package.dependencies]
+markdown-it-py = ">=2.2.0"
+pygments = ">=2.13.0,<3.0.0"
+
+[package.extras]
+jupyter = ["ipywidgets (>=7.5.1,<9)"]
+
+[[package]]
+name = "rpds-py"
+version = "0.18.1"
+description = "Python bindings to Rust's persistent data structures (rpds)"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "ruff"
+version = "0.5.0"
+description = "An extremely fast Python linter and code formatter, written in Rust."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "safetensors"
+version = "0.4.3"
+description = ""
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+numpy = ["numpy (>=1.21.6)"]
+torch = ["safetensors", "torch (>=1.10)"]
+tensorflow = ["safetensors", "tensorflow (>=2.11.0)"]
+pinned-tf = ["safetensors", "tensorflow (==2.11.0)"]
+jax = ["safetensors", "flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)"]
+mlx = ["mlx (>=0.0.9)"]
+paddlepaddle = ["safetensors", "paddlepaddle (>=2.4.1)"]
+quality = ["black (==22.3)", "click (==8.0.4)", "isort (>=5.5.4)", "flake8 (>=3.8.3)"]
+testing = ["safetensors", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "setuptools-rust (>=1.5.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "hypothesis (>=6.70.2)"]
+all = ["safetensors", "safetensors", "safetensors", "safetensors", "safetensors", "safetensors", "safetensors"]
+dev = ["safetensors"]
+
+[[package]]
+name = "scikit-learn"
+version = "1.5.0"
+description = "A set of python modules for machine learning and data mining"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[package.dependencies]
+joblib = ">=1.2.0"
+numpy = ">=1.19.5"
+scipy = ">=1.6.0"
+threadpoolctl = ">=3.1.0"
+
+[package.extras]
+build = ["numpy (>=1.19.5)", "scipy (>=1.6.0)", "cython (>=3.0.10)", "meson-python (>=0.15.0)"]
+install = ["numpy (>=1.19.5)", "scipy (>=1.6.0)", "joblib (>=1.2.0)", "threadpoolctl (>=3.1.0)"]
+benchmark = ["matplotlib (>=3.3.4)", "pandas (>=1.1.5)", "memory_profiler (>=0.57.0)"]
+docs = ["matplotlib (>=3.3.4)", "scikit-image (>=0.17.2)", "pandas (>=1.1.5)", "seaborn (>=0.9.0)", "memory_profiler (>=0.57.0)", "sphinx (>=6.0.0)", "sphinx-copybutton (>=0.5.2)", "sphinx-gallery (>=0.15.0)", "numpydoc (>=1.2.0)", "Pillow (>=7.1.2)", "pooch (>=1.6.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)", "plotly (>=5.14.0)", "polars (>=0.20.23)"]
+examples = ["matplotlib (>=3.3.4)", "scikit-image (>=0.17.2)", "pandas (>=1.1.5)", "seaborn (>=0.9.0)", "pooch (>=1.6.0)", "plotly (>=5.14.0)"]
+tests = ["matplotlib (>=3.3.4)", "scikit-image (>=0.17.2)", "pandas (>=1.1.5)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.2.1)", "black (>=24.3.0)", "mypy (>=1.9)", "pyamg (>=4.0.0)", "polars (>=0.20.23)", "pyarrow (>=12.0.0)", "numpydoc (>=1.2.0)", "pooch (>=1.6.0)"]
+maintenance = ["conda-lock (==2.5.6)"]
+
+[[package]]
+name = "scipy"
+version = "1.14.0"
+description = "Fundamental algorithms for scientific computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.10"
+
+[package.dependencies]
+numpy = ">=1.23.5,<2.3"
+
+[package.extras]
+test = ["pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "asv", "mpmath", "gmpy2", "threadpoolctl", "scikit-umfpack", "pooch", "hypothesis (>=6.30)", "array-api-strict", "cython", "meson", "ninja"]
+doc = ["sphinx (>=5.0.0)", "pydata-sphinx-theme (>=0.15.2)", "sphinx-design (>=0.4.0)", "matplotlib (>=3.5)", "numpydoc", "jupytext", "myst-nb", "pooch", "jupyterlite-sphinx (>=0.13.1)", "jupyterlite-pyodide-kernel"]
+dev = ["mypy (==1.10.0)", "typing-extensions", "types-psutil", "pycodestyle", "ruff (>=0.0.292)", "cython-lint (>=0.12.2)", "rich-click", "doit (>=0.36.0)", "pydevtool"]
+
+[[package]]
+name = "semantic-version"
+version = "2.10.0"
+description = "A library implementing the 'SemVer' scheme."
+category = "main"
+optional = false
+python-versions = ">=2.7"
+
+[package.extras]
+dev = ["Django (>=1.11)", "nose2", "tox", "check-manifest", "coverage", "flake8", "wheel", "zest.releaser", "readme-renderer (<25.0)", "colorama (<=0.4.1)"]
+doc = ["sphinx", "sphinx-rtd-theme"]
+
+[[package]]
+name = "shellingham"
+version = "1.5.4"
+description = "Tool to Detect Surrounding Shell"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "six"
+version = "1.16.0"
+description = "Python 2 and 3 compatibility utilities"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+description = "Sniff out which async library your code is running under"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "starlette"
+version = "0.37.2"
+description = "The little ASGI library that shines."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+anyio = ">=3.4.0,<5"
+
+[package.extras]
+full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.7)", "pyyaml"]
+
+[[package]]
+name = "sympy"
+version = "1.12.1"
+description = "Computer algebra system (CAS) in Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+mpmath = ">=1.1.0,<1.4.0"
+
+[[package]]
+name = "tbb"
+version = "2021.13.0"
+description = "Intel® oneAPI Threading Building Blocks (oneTBB)"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "tensorboard"
+version = "2.17.0"
+description = "TensorBoard lets you watch Tensors Flow"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[package.dependencies]
+absl-py = ">=0.4"
+grpcio = ">=1.48.2"
+markdown = ">=2.6.8"
+numpy = ">=1.12.0"
+protobuf = ">=3.19.6,<4.24.0 || >4.24.0,<5.0.0"
+six = ">1.9"
+tensorboard-data-server = ">=0.7.0,<0.8.0"
+werkzeug = ">=1.0.1"
+
+[[package]]
+name = "tensorboard-data-server"
+version = "0.7.2"
+description = "Fast data loading for TensorBoard"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "threadpoolctl"
+version = "3.5.0"
+description = "threadpoolctl"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "tokenizers"
+version = "0.19.1"
+description = ""
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+huggingface-hub = ">=0.16.4,<1.0"
+
+[package.extras]
+testing = ["pytest", "requests", "numpy", "datasets", "black (==22.3)", "ruff"]
+docs = ["sphinx", "sphinx-rtd-theme", "setuptools-rust"]
+dev = ["tokenizers"]
+
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+category = "dev"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "tomlkit"
+version = "0.12.0"
+description = "Style preserving TOML library"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "toolz"
+version = "0.12.1"
+description = "List processing tools and functional utilities"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "torch"
+version = "2.3.1"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+jinja2 = "*"
+mkl = {version = ">=2021.1.1,<=2021.4.0", markers = "platform_system == \"Windows\""}
+networkx = "*"
+nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+triton = {version = "2.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""}
+typing-extensions = ">=4.8.0"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+optree = ["optree (>=0.9.1)"]
+
+[[package]]
+name = "torchvision"
+version = "0.18.1"
+description = "image and video datasets and models for torch deep learning"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+numpy = "*"
+pillow = ">=5.3.0,<8.3.0 || >=8.4.0"
+torch = "2.3.1"
+
+[package.extras]
+scipy = ["scipy"]
+
+[[package]]
+name = "tqdm"
+version = "4.66.4"
+description = "Fast, Extensible Progress Meter"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
+name = "transformers"
+version = "4.41.2"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.23.0,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+safetensors = ">=0.4.1"
+tokenizers = ">=0.19,<0.20"
+tqdm = ">=4.27"
+
+[package.extras]
+accelerate = ["accelerate (>=0.21.0)"]
+agents = ["diffusers", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "torch", "sentencepiece (>=0.1.91,!=0.1.92)", "opencv-python", "Pillow (>=10.0.1,<=15.0)"]
+all = ["tensorflow (>2.9,<2.16)", "onnxconverter-common", "tf2onnx", "tensorflow-text (<2.16)", "keras-nlp (>=0.3.1)", "torch", "accelerate (>=0.21.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "flax (>=0.4.1,<=0.7.0)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "protobuf", "tokenizers (>=0.19,<0.20)", "torchaudio", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm", "Pillow (>=10.0.1,<=15.0)", "optuna", "ray[tune] (>=2.7.0)", "sigopt", "timm", "torchvision", "codecarbon (==1.2.0)", "decord (==0.6.0)", "av (==9.2.0)"]
+audio = ["librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["deepspeed (>=0.9.3)", "accelerate (>=0.21.0)"]
+deepspeed-testing = ["deepspeed (>=0.9.3)", "accelerate (>=0.21.0)", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "pytest-timeout", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "nltk", "GitPython (<3.1.19)", "sacremoses", "rjieba", "beautifulsoup4", "tensorboard", "pydantic", "sentencepiece (>=0.1.91,!=0.1.92)", "faiss-cpu", "cookiecutter (==1.7.3)", "optuna", "protobuf"]
+dev-tensorflow = ["rjieba", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "pytest-timeout", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "nltk", "GitPython (<3.1.19)", "sacremoses", "beautifulsoup4", "tensorboard", "pydantic", "sentencepiece (>=0.1.91,!=0.1.92)", "faiss-cpu", "cookiecutter (==1.7.3)", "tensorflow (>2.9,<2.16)", "onnxconverter-common", "tf2onnx", "tensorflow-text (<2.16)", "keras-nlp (>=0.3.1)", "protobuf", "tokenizers (>=0.19,<0.20)", "Pillow (>=10.0.1,<=15.0)", "isort (>=5.5.4)", "urllib3 (<2.0.0)", "scikit-learn", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+dev = ["tensorflow (>2.9,<2.16)", "onnxconverter-common", "tf2onnx", "tensorflow-text (<2.16)", "keras-nlp (>=0.3.1)", "torch", "accelerate (>=0.21.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "flax (>=0.4.1,<=0.7.0)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "protobuf", "tokenizers (>=0.19,<0.20)", "torchaudio", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm", "Pillow (>=10.0.1,<=15.0)", "optuna", "ray[tune] (>=2.7.0)", "sigopt", "timm", "torchvision", "codecarbon (==1.2.0)", "decord (==0.6.0)", "av (==9.2.0)", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "pytest-timeout", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "nltk", "GitPython (<3.1.19)", "sacremoses", "rjieba", "beautifulsoup4", "tensorboard", "pydantic", "faiss-cpu", "cookiecutter (==1.7.3)", "isort (>=5.5.4)", "urllib3 (<2.0.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)", "sudachipy (>=0.6.6)", "sudachidict-core (>=20220729)", "rhoknp (>=1.1.0,<1.3.1)", "scikit-learn"]
+dev-torch = ["pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "pytest-timeout", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "nltk", "GitPython (<3.1.19)", "sacremoses", "rjieba", "beautifulsoup4", "tensorboard", "pydantic", "sentencepiece (>=0.1.91,!=0.1.92)", "faiss-cpu", "cookiecutter (==1.7.3)", "torch", "accelerate (>=0.21.0)", "protobuf", "tokenizers (>=0.19,<0.20)", "torchaudio", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm", "Pillow (>=10.0.1,<=15.0)", "optuna", "ray[tune] (>=2.7.0)", "sigopt", "timm", "torchvision", "codecarbon (==1.2.0)", "isort (>=5.5.4)", "urllib3 (<2.0.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)", "sudachipy (>=0.6.6)", "sudachidict-core (>=20220729)", "rhoknp (>=1.1.0,<1.3.1)", "scikit-learn", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+flax = ["jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "flax (>=0.4.1,<=0.7.0)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"]
+flax-speech = ["librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"]
+ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)", "sudachipy (>=0.6.6)", "sudachidict-core (>=20220729)", "rhoknp (>=1.1.0,<1.3.1)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+natten = ["natten (>=0.14.6,<0.15.0)"]
+onnx = ["onnxconverter-common", "tf2onnx", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+optuna = ["optuna"]
+quality = ["datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "GitPython (<3.1.19)", "urllib3 (<2.0.0)"]
+ray = ["ray[tune] (>=2.7.0)"]
+retrieval = ["faiss-cpu", "datasets (!=2.5.0)"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["sentencepiece (>=0.1.91,!=0.1.92)", "protobuf"]
+serving = ["pydantic", "uvicorn", "fastapi", "starlette"]
+sigopt = ["sigopt"]
+sklearn = ["scikit-learn"]
+speech = ["torchaudio", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+testing = ["pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "pytest-timeout", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "nltk", "GitPython (<3.1.19)", "sacremoses", "rjieba", "beautifulsoup4", "tensorboard", "pydantic", "sentencepiece (>=0.1.91,!=0.1.92)", "faiss-cpu", "cookiecutter (==1.7.3)"]
+tf = ["tensorflow (>2.9,<2.16)", "onnxconverter-common", "tf2onnx", "tensorflow-text (<2.16)", "keras-nlp (>=0.3.1)"]
+tf-cpu = ["keras (>2.9,<2.16)", "tensorflow-cpu (>2.9,<2.16)", "onnxconverter-common", "tf2onnx", "tensorflow-text (<2.16)", "keras-nlp (>=0.3.1)", "tensorflow-probability (<2.16)"]
+tf-speech = ["librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+timm = ["timm"]
+tokenizers = ["tokenizers (>=0.19,<0.20)"]
+torch = ["torch", "accelerate (>=0.21.0)"]
+torch-speech = ["torchaudio", "librosa", "pyctcdecode (>=0.4.0)", "phonemizer", "kenlm"]
+torch-vision = ["torchvision", "Pillow (>=10.0.1,<=15.0)"]
+torchhub = ["filelock", "huggingface-hub (>=0.23.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "torch", "tokenizers (>=0.19,<0.20)", "tqdm (>=4.27)"]
+video = ["decord (==0.6.0)", "av (==9.2.0)"]
+vision = ["Pillow (>=10.0.1,<=15.0)"]
+
+[[package]]
+name = "triton"
+version = "2.3.1"
+description = "A language and compiler for custom Deep Learning operations"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+filelock = "*"
+
+[package.extras]
+build = ["cmake (>=3.20)", "lit"]
+tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
+tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
+
+[[package]]
+name = "typer"
+version = "0.12.3"
+description = "Typer, build great CLIs. Easy to code. Based on Python type hints."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+click = ">=8.0.0"
+rich = ">=10.11.0"
+shellingham = ">=1.3.0"
+typing-extensions = ">=3.7.4.3"
+
+[[package]]
+name = "typing-extensions"
+version = "4.12.2"
+description = "Backported and Experimental Type Hints for Python 3.8+"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "tzdata"
+version = "2024.1"
+description = "Provider of IANA time zone data"
+category = "main"
+optional = false
+python-versions = ">=2"
+
+[[package]]
+name = "ujson"
+version = "5.10.0"
+description = "Ultra fast JSON encoder and decoder for Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "urllib3"
+version = "2.2.2"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+h2 = ["h2 (>=4,<5)"]
+socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
+zstd = ["zstandard (>=0.18.0)"]
+
+[[package]]
+name = "uvicorn"
+version = "0.30.1"
+description = "The lightning-fast ASGI server."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+click = ">=7.0"
+colorama = {version = ">=0.4", optional = true, markers = "sys_platform == \"win32\" and extra == \"standard\""}
+h11 = ">=0.8"
+httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standard\""}
+python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
+pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
+typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
+uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
+watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
+websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
+
+[package.extras]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+
+[[package]]
+name = "uvloop"
+version = "0.19.0"
+description = "Fast implementation of asyncio event loop on top of libuv"
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+
+[package.extras]
+docs = ["Sphinx (>=4.1.2,<4.2.0)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)", "sphinx-rtd-theme (>=0.5.2,<0.6.0)"]
+test = ["flake8 (>=5.0,<6.0)", "psutil", "pycodestyle (>=2.9.0,<2.10.0)", "pyOpenSSL (>=23.0.0,<23.1.0)", "mypy (>=0.800)", "Cython (>=0.29.36,<0.30.0)", "aiohttp (>=3.8.1)", "aiohttp (==3.9.0b0)"]
+
+[[package]]
+name = "vulture"
+version = "2.11"
+description = "Find dead code"
+category = "dev"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
+
+[[package]]
+name = "watchfiles"
+version = "0.22.0"
+description = "Simple, modern and high performance file watching and code reload in python."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+anyio = ">=3.0.0"
+
+[[package]]
+name = "websockets"
+version = "11.0.3"
+description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "werkzeug"
+version = "3.0.3"
+description = "The comprehensive WSGI web application library."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+MarkupSafe = ">=2.1.1"
+
+[package.extras]
+watchdog = ["watchdog (>=2.3)"]
+
+[metadata]
+lock-version = "1.1"
+python-versions = "^3.10"
+content-hash = "b2c34c8c67b16bae88499909078bb65a8829aa3a72b539871b2f1baf30eb9e11"
+
+[metadata.files]
+absl-py = []
+aiofiles = []
+altair = []
+annotated-types = []
+anyio = []
+attrs = []
+black = []
+certifi = []
+charset-normalizer = []
+click = []
+colorama = []
+contourpy = []
+cycler = []
+dnspython = []
+email-validator = []
+exceptiongroup = []
+fastapi = []
+fastapi-cli = []
+ffmpy = []
+filelock = []
+flake8 = []
+fonttools = []
+fsspec = []
+gradio = []
+gradio-client = []
+grpcio = []
+h11 = []
+httpcore = []
+httptools = []
+httpx = []
+huggingface-hub = []
+idna = []
+importlib-resources = []
+intel-openmp = []
+jinja2 = []
+joblib = []
+jsonschema = []
+jsonschema-specifications = []
+kiwisolver = []
+markdown = []
+markdown-it-py = []
+markupsafe = []
+matplotlib = []
+mccabe = []
+mdurl = []
+mkl = []
+mpmath = []
+mypy = []
+mypy-extensions = []
+networkx = []
+numpy = []
+nvidia-cublas-cu12 = []
+nvidia-cuda-cupti-cu12 = []
+nvidia-cuda-nvrtc-cu12 = []
+nvidia-cuda-runtime-cu12 = []
+nvidia-cudnn-cu12 = []
+nvidia-cufft-cu12 = []
+nvidia-curand-cu12 = []
+nvidia-cusolver-cu12 = []
+nvidia-cusparse-cu12 = []
+nvidia-nccl-cu12 = []
+nvidia-nvjitlink-cu12 = []
+nvidia-nvtx-cu12 = []
+orjson = []
+packaging = []
+pandas = []
+pathspec = []
+pillow = []
+platformdirs = []
+protobuf = []
+pycodestyle = []
+pydantic = []
+pydantic-core = []
+pydub = []
+pyflakes = []
+pygments = []
+pyparsing = []
+python-dateutil = []
+python-dotenv = []
+python-multipart = []
+pytz = []
+pyyaml = []
+referencing = []
+regex = []
+requests = []
+rich = []
+rpds-py = []
+ruff = []
+safetensors = []
+scikit-learn = []
+scipy = []
+semantic-version = []
+shellingham = []
+six = []
+sniffio = []
+starlette = []
+sympy = []
+tbb = []
+tensorboard = []
+tensorboard-data-server = []
+threadpoolctl = []
+tokenizers = []
+tomli = []
+tomlkit = []
+toolz = []
+torch = []
+torchvision = []
+tqdm = []
+transformers = []
+triton = []
+typer = []
+typing-extensions = []
+tzdata = []
+ujson = []
+urllib3 = []
+uvicorn = []
+uvloop = []
+vulture = []
+watchfiles = []
+websockets = []
+werkzeug = []

pyproject.toml

@@ -0,0 +1,31 @@
+[tool.poetry]
+name = "makeitsports-bot"
+version = "0.1.0"
+description = ""
+authors = ["brunorosilva <b.rosilva1@gmail.com>"]
+readme = "README.md"
+packages = [{include = "makeitsports_bot"}]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+torch = "^2.3.1"
+torchvision = "^0.18.1"
+tqdm = "^4.66.4"
+pandas = "^2.2.2"
+scipy = "^1.14.0"
+numpy = "^2.0.0"
+transformers = "^4.41.2"
+tensorboard = "^2.17.0"
+scikit-learn = ">=0.0.0"
+matplotlib = "^3.9.0"
+gradio = ">=0.0.0"
+
+
+[tool.poetry.dev-dependencies]
+black = "^24.4.2"
+vulture = "^2.11"
+mypy = "^1.10.1"
+flake8 = "^7.1.0"
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

setup.cfg

@@ -0,0 +1,7 @@
+[flake8]
+max-line-length = 88
+ignore = E122,E123,E126,E127,E128,E203,E221,E241,E731,E722,W503
+exclude = tests,.git,__init__.py
+
+[bdist_wheel]
+universal=1

setup.py

@@ -0,0 +1,36 @@
+import io
+import os
+import re
+
+from setuptools import find_packages
+from setuptools import setup
+
+
+def read(filename):
+    filename = os.path.join(os.path.dirname(__file__), filename)
+    text_type = type("")
+    with io.open(filename, mode="r", encoding="utf-8") as fd:
+        return re.sub(text_type(r":[a-z]+:`~?(.*?)`"), text_type(r"``\1``"), fd.read())
+
+
+requirements = [
+    # use environment.yml
+]
+
+
+setup(
+    name="makeitsports_bot",
+    version="0.0.1",
+    url="https://github.com/brunorosilva/makeitsports-bot",
+    author="Bruno Chicelli",
+    author_email="chicelli@outlook.com",
+    description="Short description",
+    long_description=read("README.rst"),
+    packages=find_packages(exclude=("tests",)),
+    entry_points={"console_scripts": ["makeitsports_bot=makeitsports_bot.cli:cli"]},
+    install_requires=requirements,
+    classifiers=[
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 3.6",
+    ],
+)