rename script to avoid clash with package name

.isort.cfg

@@ -8,4 +8,4 @@ line_length = 88
 
 default_section=FIRSTPARTY
 known_first_party =
-known_third_party = PIL,apistar,arkindex,cv2,numpy,pytest,requests,setuptools,tqdm
+known_third_party = PIL,cv2,numpy,pytest,requests,setuptools

README.md

@@ -9,33 +9,33 @@ and converts data to Kaldi format or kraken format. It also generates train, val
 
 `ARKINDEX_API_TOKEN` and `ARKINDEX_API_URL` environment variables must be defined.
 
-Install necessary dependencies
+Install it as a package
 ```bash
 virtualenv -p python3 .env
 source .env/bin/activate
-pip install -r requirements.txt
+pip install -e .
 ```
 
 Use help to list possible parameters:
 ```bash
-python kaldi_data_generator.py --help
+kaldi-data-generator --help
 ```
 
 There is also an option that skips all vertical transcriptions and it is `--skip_vertical_lines`
 #### Kaldi format
 Simple example:
 ```bash
-python kaldi_data_generator.py -f kaldi --dataset_name my_balsac --out_dir /tmp/balsac/ --volumes 8f4005e9-1921-47b0-be7b-e27c7fd29486  d2f7c563-1622-4721-bd51-96fab97189f7
+kaldi-data-generator -f kaldi --dataset_name my_balsac --out_dir /tmp/balsac/ --volumes 8f4005e9-1921-47b0-be7b-e27c7fd29486  d2f7c563-1622-4721-bd51-96fab97189f7
 ```
 
 With corpus ids
 ```bash
-python kaldi_data_generator.py -f kaldi --dataset_name cz --out_dir /tmp/home_cz/ --corpora 1ed45e94-9108-4029-a529-9abe37f55ba0
+kaldi-data-generator -f kaldi --dataset_name cz --out_dir /tmp/home_cz/ --corpora 1ed45e94-9108-4029-a529-9abe37f55ba0
 ```
 
 Polygon example:
 ```bash
-python kaldi_data_generator.py -f kaldi --dataset_name my_balsac2 --extraction_mode polygon --out_dir /tmp/balsac/ --pages 50e1c3c0-2fe9-4216-805e-1a2fd2e7e9f4
+kaldi-data-generator -f kaldi --dataset_name my_balsac2 --extraction_mode polygon --out_dir /tmp/balsac/ --pages 50e1c3c0-2fe9-4216-805e-1a2fd2e7e9f4
 ```
 
 The script creates 3 directories `Lines`, `Transcriptions`, `Partitions` in the specified `out_dir`.
@@ -45,13 +45,13 @@ The contents of these directories must be copied (or symlinked) to the correspon
 
 simple examples:
 ```
-$ python3 kaldi_data_generator.py -f kraken -o <output_dir> --volumes <volume_id> --no_split
+$ kaldi-data-generator -f kraken -o <output_dir> --volumes <volume_id> --no_split
 ```
 For instance to download the 4 sets from IAM (2 validation set on Arkindex) in 3 directories :
 ```
-$ python3 kaldi_data_generator.py -f kraken -o iam_training --volumes e7a95479-e5fc-4b20-830c-0c6e38bf8f72 --no_split
-$ python3 kaldi_data_generator.py -f kraken -o iam_validation --volumes edc78ee1-09e0-4671-806b-5fc0392707d9 --no_split
-$ python3 kaldi_data_generator.py -f kraken -o iam_validation --volumes fefbbfca-a6dd-4e00-8797-0d4628cb024d --no_split
-$ python3 kaldi_data_generator.py -f kraken -o iam_test --volumes 0ce2b631-01d7-49bf-b213-ceb6eae74a9b --no_split
+$ kaldi-data-generator -f kraken -o iam_training --volumes e7a95479-e5fc-4b20-830c-0c6e38bf8f72 --no_split
+$ kaldi-data-generator -f kraken -o iam_validation --volumes edc78ee1-09e0-4671-806b-5fc0392707d9 --no_split
+$ kaldi-data-generator -f kraken -o iam_validation --volumes fefbbfca-a6dd-4e00-8797-0d4628cb024d --no_split
+$ kaldi-data-generator -f kraken -o iam_test --volumes 0ce2b631-01d7-49bf-b213-ceb6eae74a9b --no_split
 ```
 

setup.py

@@ -22,6 +22,6 @@ setup(
     author="Martin",
     author_email="maarand@teklia.com",
     install_requires=parse_requirements(),
-    entry_points={"console_scripts": [f"{COMMAND}={MODULE}.kaldi_data_generator:main"]},
+    entry_points={"console_scripts": [f"{COMMAND}={MODULE}.main:main"]},
     packages=find_packages(),
 )