support subtitle batch alignment

Makefile

@@ -34,12 +34,18 @@ install:
 	.$(PYTHON)/bin/pip install -e . --ignore-installed
 	cp ./bin/subaligner_1pass .$(PYTHON)/bin/subaligner_1pass
 	cp ./bin/subaligner_2pass .$(PYTHON)/bin/subaligner_2pass
+	cp ./bin/subaligner_batch .$(PYTHON)/bin/subaligner_batch
+	cp ./bin/subaligner_convert .$(PYTHON)/bin/subaligner_convert
+	cp ./bin/subaligner_train .$(PYTHON)/bin/subaligner_train
+	cp ./bin/subaligner_tune .$(PYTHON)/bin/subaligner_tune
 	cp ./bin/subaligner .$(PYTHON)/bin/subaligner
 
 uninstall:
 	rm -f .$(PYTHON)/bin/subaligner
 	rm -f .$(PYTHON)/bin/subaligner_1pass
 	rm -f .$(PYTHON)/bin/subaligner_2pass
+	rm -f .$(PYTHON)/bin/subaligner_batch
+	rm -f .$(PYTHON)/bin/subaligner_convert
 	rm -f .$(PYTHON)/bin/subaligner_train
 	rm -f .$(PYTHON)/bin/subaligner_tune
 
@@ -57,7 +63,7 @@ test:
 	cat requirements.txt | xargs -L 1 .$(PYTHON)/bin/pip install; \
 	cat requirements-dev.txt | xargs -L 1 .$(PYTHON)/bin/pip install
 	PYTHONPATH=. .$(PYTHON)/bin/python -m unittest discover
-	-.$(PYTHON)/bin/pycodestyle subaligner tests examples misc bin/subaligner bin/subaligner_1pass bin/subaligner_2pass bin/subaligner_train  bin/subaligner_tune setup.py --ignore=E203,E501,W503 --exclude="subaligner/lib"
+	-.$(PYTHON)/bin/pycodestyle subaligner tests examples misc bin/subaligner bin/subaligner_1pass bin/subaligner_2pass bin/subaligner_batch bin/subaligner_convert bin/subaligner_train  bin/subaligner_tune setup.py --ignore=E203,E501,W503 --exclude="subaligner/lib"
 
 test-all: ## run tests on every Python version with tox
 	.$(PYTHON)/bin/tox
@@ -79,17 +85,18 @@ pydoc: clean-doc ## generate pydoc HTML documentation based on docstrings
 	cat requirements.txt | xargs -L 1 .$(PYTHON)/bin/pip install; \
 	.$(PYTHON)/bin/python -m pydoc -w subaligner; mv subaligner.html docs/index.html
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.embedder; mv subaligner.embedder.html docs
+	.$(PYTHON)/bin/python -m pydoc -w subaligner.exception; mv subaligner.exception.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.hparam_tuner; mv subaligner.hparam_tuner.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.hyperparameters; mv subaligner.hyperparameters.html docs
+	.$(PYTHON)/bin/python -m pydoc -w subaligner.logger; mv subaligner.logger.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.media_helper; mv subaligner.media_helper.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.network; mv subaligner.network.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.predictor; mv subaligner.predictor.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.singleton; mv subaligner.singleton.html docs
+	.$(PYTHON)/bin/python -m pydoc -w subaligner.subtitle; mv subaligner.subtitle.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.trainer; mv subaligner.trainer.html docs
+	.$(PYTHON)/bin/python -m pydoc -w subaligner.translator; mv subaligner.translator.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner.utils; mv subaligner.utils.html docs
-	.$(PYTHON)/bin/python -m pydoc -w subaligner.subtitle; mv subaligner.subtitle.html docs
-	.$(PYTHON)/bin/python -m pydoc -w subaligner.logger; mv subaligner.logger.html docs
-	.$(PYTHON)/bin/python -m pydoc -w subaligner.exception; mv subaligner.exception.html docs
 	.$(PYTHON)/bin/python -m pydoc -w subaligner._version; mv subaligner._version.html docs
 	$(BROWSER) docs/index.html
 

README.md

@@ -94,6 +94,12 @@ $ subaligner -m single -v video.mp4 -s subtitle.srt -t src,tgt
 $ subaligner -m dual -v video.mp4 -s subtitle.srt -t src,tgt
 ```
 ```
+# Run batch alignment
+
+$ subaligner_batch -m single -vd /videos -sd /subtitles -od /aligned_subtitles
+$ subaligner_batch -m dual -vd /videos -sd /subtitles -od /aligned_subtitles
+```
+```
 # Run alignments with pipx
 
 $ pipx run subaligner -m single -v video.mp4 -s subtitle.srt
@@ -116,7 +122,7 @@ $ docker run -it baxtree/subaligner subaligner_1pass -v https://example.com/vide
 $ docker run -it baxtree/subaligner subaligner_2pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
 ```
 The aligned subtitle will be saved at `subtitle_aligned.srt`. For details on CLI, run `subaligner_1pass -h`, `subaligner_2pass -h` or `subaligner -h`.
-Additional utilities can be used after consulting `subaligner_convert -h`, `subaligner_train -h` and `subaligner_tune -h`.
+Additional utilities can be used after consulting `subaligner_batch -h`, `subaligner_convert -h`, `subaligner_train -h` and `subaligner_tune -h`.
 
 ![](figures/screencast.gif)
 ## Supported Formats

bin/subaligner_batch

@@ -0,0 +1 @@
+../subaligner/subaligner_batch/__main__.py

setup.py

@@ -40,6 +40,7 @@
           "subaligner.lib",
           "subaligner.subaligner_1pass",
           "subaligner.subaligner_2pass",
+          "subaligner.subaligner_batch",
           "subaligner.subaligner_convert",
           "subaligner.subaligner_train",
           "subaligner.subaligner_tune",
@@ -59,6 +60,7 @@
           "bin/subaligner",
           "bin/subaligner_1pass",
           "bin/subaligner_2pass",
+          "bin/subaligner_batch",
           "bin/subaligner_convert",
           "bin/subaligner_train",
           "bin/subaligner_tune",
@@ -68,6 +70,7 @@
               "subaligner=subaligner.__main__:main",
               "subaligner_1pass=subaligner.subaligner_1pass.__main__:main",
               "subaligner_2pass=subaligner.subaligner_2pass.__main__:main",
+              "subaligner_batch=subaligner.subaligner_batch.__main__:main",
               "subaligner_convert=subaligner.subaligner_convert.__main__:main",
               "subaligner_train=subaligner.subaligner_train.__main__:main",
               "subaligner_tune=subaligner.subaligner_tune.__main__:main",

site/source/installation.rst

@@ -54,6 +54,8 @@ to create a virtual environment and set up all the dependencies:
     (.venv) $ subaligner --help
     (.venv) $ subaligner_1pass --help
     (.venv) $ subaligner_2pass --help
+    (.venv) $ subaligner_batch --help
+    (.venv) $ subaligner_convert --help
     (.venv) $ subaligner_train --help
     (.venv) $ subaligner_tune --help
 

site/source/usage.rst

@@ -36,6 +36,11 @@ Make sure you have got the virtual environment activated upfront.
     (.venv) $ subaligner -m single -v video.mp4 -s subtitle.srt -t src,tgt
     (.venv) $ subaligner -m dual -v video.mp4 -s subtitle.srt -t src,tgt
 
+**Run batch alignment**::
+
+    (.venv) $ subaligner_batch -m single -vd /videos -sd /subtitles -od /aligned_subtitles
+    (.venv) $ subaligner_batch -m dual -vd /videos -sd /subtitles -od /aligned_subtitles
+
 **Run alignments with the docker image**::
 
     $ docker pull baxtree/subaligner

subaligner/__main__.py

@@ -140,18 +140,23 @@ def main():
         sys.exit(0)
     if FLAGS.mode == "":
         print("--mode was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.video_path == "":
         print("--video_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path == "":
         print("--subtitle_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("http") and FLAGS.output == "":
         print("--output was not passed in for alignment on a remote subtitle file")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("teletext:") and FLAGS.output == "":
         print("--output was not passed in for alignment on embedded subtitles")
+        parser.print_usage()
         sys.exit(21)
 
     local_video_path = FLAGS.video_path
@@ -194,6 +199,7 @@ def main():
                     Utils.extract_matroska_subtitle(local_video_path, int(params["stream_index"]), local_subtitle_path)
             else:
                 print("Embedded subtitle selector cannot be empty")
+                parser.print_usage()
                 sys.exit(21)
 
         predictor = Predictor()

subaligner/subaligner_1pass/__main__.py

@@ -103,15 +103,19 @@ def main():
         sys.exit(0)
     if FLAGS.video_path == "":
         print("--video_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path == "":
         print("--subtitle_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("http") and FLAGS.output == "":
         print("--output was not passed in for alignment on a remote subtitle file")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("teletext:") and FLAGS.output == "":
         print("--output was not passed in for alignment on embedded subtitles")
+        parser.print_usage()
         sys.exit(21)
 
     local_video_path = FLAGS.video_path
@@ -151,6 +155,7 @@ def main():
                     Utils.extract_matroska_subtitle(local_video_path, int(params["stream_index"]), local_subtitle_path)
             else:
                 print("Embedded subtitle selector cannot be empty")
+                parser.print_usage()
                 sys.exit(21)
 
         predictor = Predictor()

subaligner/subaligner_2pass/__main__.py

@@ -130,15 +130,19 @@ def main():
         sys.exit(0)
     if FLAGS.video_path == "":
         print("--video_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path == "":
         print("--subtitle_path was not passed in")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("http") and FLAGS.output == "":
         print("--output was not passed in for alignment on a remote subtitle file")
+        parser.print_usage()
         sys.exit(21)
     if FLAGS.subtitle_path.lower().startswith("teletext:") and FLAGS.output == "":
         print("--output was not passed in for alignment on embedded subtitles")
+        parser.print_usage()
         sys.exit(21)
 
     local_video_path = FLAGS.video_path
@@ -181,6 +185,7 @@ def main():
                     Utils.extract_matroska_subtitle(local_video_path, int(params["stream_index"]), local_subtitle_path)
             else:
                 print("Embedded subtitle selector cannot be empty")
+                parser.print_usage()
                 sys.exit(21)
 
         predictor = Predictor()