post relase tidy up

baxtree · Mar 14, 2023 · f05f4d7 · f05f4d7
1 parent 197495f
commit f05f4d7
Show file tree

Hide file tree

Showing 16 changed files with 256 additions and 251 deletions.
diff --git a/CITATION.cff b/CITATION.cff
@@ -5,7 +5,6 @@ authors:
     given-names: Xi
     orcid: https://orcid.org/0000-0002-2177-8458
 title: "Subaligner: Towards Automated Subtitle Alignment"
-version: 0.2.1
 doi: 10.5281/zenodo.5603083
 date-released: 2021-10-28
 url: "https://github.com/baxtree/subaligner"
diff --git a/README.md b/README.md
@@ -31,6 +31,12 @@ $ brew install ffmpeg
 $ pip install -U pip
 $ pip install subaligner
 ```
+or install from source:
+```
+$ git clone [email protected]:baxtree/subaligner.git
+$ cd subaligner
+$ python setup.py install
+```
 
 ## Installation with Optional Packages Supporting Additional Features
 ```
@@ -61,31 +67,10 @@ To install all supported features:
 $ pip install 'subaligner[harmony]'
 ```
 
-## Alternative Installations
-```
-# Install via pipx
-$ pip install -U pip pipx
-$ pipx install subaligner
-```
-or
-```
-# Install from GitHub via Pipenv
-$ pipenv install subaligner
-$ pipenv install 'subaligner[stretch]'
-$ pipenv install 'subaligner[dev]'
-```
-or
-```
-# Install from source
+## Container Support
+If you prefer using a containerised environment over installing everything locally, run:
 
-$ git clone [email protected]:baxtree/subaligner.git
-$ cd subaligner
-$ python setup.py install
-```
-or
 ```
-# Use dockerised installation
-
 $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner bash
 ```
 For users on Windows 10: [Docker Desktop](https://docs.docker.com/docker-for-windows/install/) is the only option at present.
@@ -99,22 +84,13 @@ docker run -v "/d/media":/media -w "/media" -it baxtree/subaligner bash
 ```
 # Single-stage alignment (high-level shift with lower latency)
 
-$ subaligner_1pass -v video.mp4 -s subtitle.srt
-$ subaligner_1pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
+$ subaligner -m single -v video.mp4 -s subtitle.srt
+$ subaligner -m single -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
 ```
 ```
 # Dual-stage alignment (low-level shift with higher latency)
 
-$ subaligner_2pass -v video.mp4 -s subtitle.srt
-$ subaligner_2pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
-```
-or
-```
-# Pass in single-stage or dual-stage as the alignment mode
-
-$ subaligner -m single -v video.mp4 -s subtitle.srt
 $ subaligner -m dual -v video.mp4 -s subtitle.srt
-$ subaligner -m single -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
 $ subaligner -m dual -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
 ```
 ```
@@ -142,6 +118,7 @@ $ subaligner -m dual -v video.mkv -s embedded:stream_index=0 -o subtitle_aligned
 ```
 ```
 # Translative alignment with the ISO 639-3 language code pair (src,tgt)
+
 $ subaligner --languages
 $ subaligner -m single -v video.mp4 -s subtitle.srt -t src,tgt
 $ subaligner -m dual -v video.mp4 -s subtitle.srt -t src,tgt
@@ -171,20 +148,17 @@ $ pipx run subaligner -m dual -v video.mp4 -s subtitle.srt
 # Run the module as a script
 $ python -m subaligner -m single -v video.mp4 -s subtitle.srt
 $ python -m subaligner -m dual -v video.mp4 -s subtitle.srt
-$ python -m subaligner.subaligner_1pass -v video.mp4 -s subtitle.srt
-$ python -m subaligner.subaligner_2pass -v video.mp4 -s subtitle.srt
 ```
 ```
 # Run alignments with the docker image
 
 $ docker pull baxtree/subaligner
-$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_1pass -v video.mp4 -s subtitle.srt
-$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_2pass -v video.mp4 -s subtitle.srt
-$ docker run -it baxtree/subaligner subaligner_1pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
-$ docker run -it baxtree/subaligner subaligner_2pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
+$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner -m single -v video.mp4 -s subtitle.srt
+$ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner -m dual -v video.mp4 -s subtitle.srt
+$ docker run -it baxtree/subaligner subaligner -m single -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
+$ docker run -it baxtree/subaligner subaligner -m dual -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_batch -h`, `subaligner_convert -h`, `subaligner_train -h` and `subaligner_tune -h`.
+The aligned subtitle will be saved at `subtitle_aligned.srt`. For details on CLIs, run `subaligner -h` or `subaligner_batch -h`, `subaligner_convert -h`, `subaligner_train -h` and `subaligner_tune -h` for additional utilities. `subaligner_1pass` and `subaligner_2pass` are shortcuts for running `subaligner` with `-m single` and `-m dual` options, respectively.
 
 ![](figures/screencast.gif)
 

diff --git a/site/source/advanced_usage.rst b/site/source/advanced_usage.rst
@@ -64,8 +64,6 @@ is present, make sure the folder passed in is empty.
 
     (.venv) $ subaligner -m single -v video.mp4 -s subtitle.srt -tod training_output_directory
     (.venv) $ subaligner -m dual -v video.mp4 -s subtitle.srt -tod training_output_directory
-    (.venv) $ subaligner_1pass -v video.mp4 -s subtitle.srt -tod training_output_directory
-    (.venv) $ subaligner_2pass -v video.mp4 -s subtitle.srt -tod training_output_directory
 
 To apply your trained model to subtitle alignment, pass in the training_output_directory containing training results as
 shown above with `-tod` or `--training_output_directory`.

diff --git a/site/source/installation.rst b/site/source/installation.rst
@@ -53,11 +53,11 @@ Installation
     $ pipenv install 'subaligner[stretch]'
     $ pipenv install 'subaligner[dev]'
 
-**Use dockerised installation**::
+**Container Support**::
 
     $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner bash
 
-The following builds are available on dockerhub for several Linux distributions: CentOS 7 (latest and VERSION.el7), CentOS 8 (VERSION.el8), Ubuntu 18 (VERSION.u18), Ubuntu 20 (VERSION.u20), Debian 10 (VERSION.deb10), Fedora 31 (VERSION.fed31) and ArchLinux (VERSION.arch).
+Users may prefer using a containerised environment over installing everything locally. The following builds are available on dockerhub for several Linux distributions: CentOS 7 (latest and VERSION.el7), CentOS 8 (VERSION.el8), Ubuntu 18 (VERSION.u18), Ubuntu 20 (VERSION.u20), Debian 10 (VERSION.deb10), Fedora 31 (VERSION.fed31) and ArchLinux (VERSION.arch).
 
 You can also download the latest
 release on `GitHub <https://github.com/baxtree/subaligner>`_ and follow the steps down below
@@ -72,8 +72,8 @@ to create a virtual environment and set up all the dependencies:
 **Subaligner CLI should be on your PATH now**::
 
     (.venv) $ subaligner --help
-    (.venv) $ subaligner_1pass --help
-    (.venv) $ subaligner_2pass --help
+    (.venv) $ subaligner_1pass --help # shortcut for "subaligner -m single"
+    (.venv) $ subaligner_2pass --help # shortcut for "subaligner -m dual"
     (.venv) $ subaligner_batch --help
     (.venv) $ subaligner_convert --help
     (.venv) $ subaligner_train --help

diff --git a/site/source/usage.rst b/site/source/usage.rst
@@ -14,18 +14,11 @@ Make sure you have got the virtual environment activated upfront.
 
 **Single-stage alignment (high-level shift with lower latency)**::
 
-    (.venv) $ subaligner_1pass -v video.mp4 -s subtitle.srt
-    (.venv) $ subaligner_1pass -v https://example.org/video.mp4 -s https://example.org/subtitle.srt -o subtitle_aligned.srt
+    (.venv) $ subaligner -m single -v video.mp4 -s subtitle.srt
+    (.venv) $ subaligner -m single -v https://example.org/video.mp4 -s https://example.org/subtitle.srt -o subtitle_aligned.srt
 
 **Dual-stage alignment (low-level shift with higher latency)**::
 
-    (.venv) $ subaligner_2pass -v video.mp4 -s subtitle.srt
-    (.venv) $ subaligner_2pass -v https://example.org/video.mp4 -s https://example.org/subtitle.srt -o subtitle_aligned.srt
-
-**Pass in single-stage or dual-stage as the alignment mode**::
-
-    (.venv) $ subaligner -m single -v video.mp4 -s subtitle.srt
-    (.venv) $ subaligner -m single -v https://example.org/video.mp4 -s https://example.org/subtitle.srt -o subtitle_aligned.srt
     (.venv) $ subaligner -m dual -v video.mp4 -s subtitle.srt
     (.venv) $ subaligner -m dual -v https://example.org/video.mp4 -s https://example.org/subtitle.srt -o subtitle_aligned.srt
 
@@ -72,10 +65,10 @@ Make sure you have got the virtual environment activated upfront.
 **Run alignments with the docker image**::
 
     $ docker pull baxtree/subaligner
-    $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_1pass -v video.mp4 -s subtitle.srt
-    $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner_2pass -v video.mp4 -s subtitle.srt
-    $ docker run -it baxtree/subaligner subaligner_1pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
-    $ docker run -it baxtree/subaligner subaligner_2pass -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
+    $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner -m single -v video.mp4 -s subtitle.srt
+    $ docker run -v `pwd`:`pwd` -w `pwd` -it baxtree/subaligner subaligner -m dual -v video.mp4 -s subtitle.srt
+    $ docker run -it baxtree/subaligner subaligner -m single -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
+    $ docker run -it baxtree/subaligner subaligner -m dual -v https://example.com/video.mp4 -s https://example.com/subtitle.srt -o subtitle_aligned.srt
 
 **Run alignments with pipx**::
 
@@ -86,22 +79,16 @@ Make sure you have got the virtual environment activated upfront.
 
     $ python -m subaligner -m single -v video.mp4 -s subtitle.srt
     $ python -m subaligner -m dual -v video.mp4 -s subtitle.srt
-    $ python -m subaligner.subaligner_1pass -v video.mp4 -s subtitle.srt
-    $ python -m subaligner.subaligner_2pass -v video.mp4 -s subtitle.srt
 
 Currently the stretching is experimental and make sure subaligner[stretch] is installed before switching it on with `-so`
 or `--stretch_on` as shown below.
 
 **Switch on stretching when aligning subtitles**::
 
-    (.venv) $ subaligner_2pass -v video.mp4 -s subtitle.srt -so
-    or
     (.venv) $ subaligner -m dual -v video.mp4 -s subtitle.srt -so
 
 **Save the aligned subtitle to a specific location**::
 
-    (.venv) $ subaligner_2pass -v video.mp4 -s subtitle.srt -o /path/to/the/output/subtitle.srt
-    or
     (.venv) $ subaligner -m dual -v video.mp4 -s subtitle.srt -o /path/to/the/output/subtitle.srt
 
 **On Windows**::

diff --git a/subaligner/__init__.py b/subaligner/__init__.py
@@ -1,7 +1,12 @@
 import os
+import warnings
 import multiprocessing as mp
 from ._version import __version__
 
 __all__ = ["__version__"]
+
+warnings.filterwarnings("ignore")
+warnings.simplefilter("ignore")
+
 mp.set_start_method("spawn", force=True)
 os.environ["KMP_WARNINGS"] = "0"
diff --git a/subaligner/__main__.py b/subaligner/__main__.py
@@ -4,14 +4,15 @@
                   [-sil {afr,amh,ara,arg,asm,aze,ben,bos,bul,cat,ces,cmn,cym,dan,deu,ell,eng,epo,est,eus,fas,fin,fra,gla,gle,glg,grc,grn,guj,heb,hin,hrv,hun,hye,ina,ind,isl,ita,jbo,jpn,kal,kan,kat,kir,kor,kur,lat,lav,lfn,lit,mal,mar,mkd,mlt,msa,mya,nah,nep,nld,nor,ori,orm,pan,pap,pol,por,ron,rus,sin,slk,slv,spa,sqi,srp,swa,swe,tam,tat,tel,tha,tsn,tur,ukr,urd,vie,yue,zho}]
                   [-fos] [-tod TRAINING_OUTPUT_DIRECTORY] [-o OUTPUT] [-t TRANSLATE] [-os OFFSET_SECONDS]
                   [-ml {afr,amh,ara,arg,asm,aze,ben,bos,bul,cat,ces,cmn,cym,dan,deu,ell,eng,epo,est,eus,fas,fin,fra,gla,gle,glg,grc,grn,guj,heb,hin,hrv,hun,hye,ina,ind,isl,ita,jbo,jpn,kal,kan,kat,kir,kor,kur,lat,lav,lfn,lit,mal,mar,mkd,mlt,msa,mya,nah,nep,nld,nor,ori,orm,pan,pap,pol,por,ron,rus,sin,slk,slv,spa,sqi,srp,swa,swe,tam,tat,tel,tha,tsn,tur,ukr,urd,vie,yue,zho}]
-                  [-mr {whisper}] [-mf {tiny,tiny.en,small,medium,medium.en,base,base.en,large-v1,large-v2,large}] [-lgs] [-d] [-q] [-ver]
+                  [-mr {whisper}] [-mf {tiny,tiny.en,small,medium,medium.en,base,base.en,large-v1,large-v2,large}] [-tr {helsinki-nlp,whisper}] [-tf TRANSLATION_FLAVOUR] [-lgs]
+                  [-d] [-q] [-ver]
 
 Subaligner command line interface
 
 optional arguments:
   -h, --help            show this help message and exit
   -s SUBTITLE_PATH [SUBTITLE_PATH ...], --subtitle_path SUBTITLE_PATH [SUBTITLE_PATH ...]
-                        File path or URL to the subtitle file (Extensions of supported subtitles: .ssa, .vtt, .srt, .txt, .smi, .ytt, .sub, .xml, .sbv, .ass, .sami, .scc, .tmp, .stl, .ttml, .dfxp) or selector for the embedded subtitle (e.g., embedded:page_num=888 or embedded:stream_index=0)
+                        File path or URL to the subtitle file (Extensions of supported subtitles: .ttml, .sub, .ytt, .smi, .sami, .tmp, .txt, .ssa, .vtt, .stl, .xml, .ass, .scc, .dfxp, .sbv, .srt) or selector for the embedded subtitle (e.g., embedded:page_num=888 or embedded:stream_index=0)
   -l MAX_LOGLOSS, --max_logloss MAX_LOGLOSS
                         Max global log loss for alignment
   -so, --stretch_on     Switch on stretch on subtitles)
@@ -32,7 +33,11 @@
   -mr {whisper}, --llm_recipe {whisper}
                         LLM recipe used for transcribing video files
   -mf {tiny,tiny.en,small,medium,medium.en,base,base.en,large-v1,large-v2,large}, --llm_flavour {tiny,tiny.en,small,medium,medium.en,base,base.en,large-v1,large-v2,large}
-                        Flavour variation for a specific LLM recipe
+                        Flavour variation for a specific LLM recipe supporting transcription
+  -tr {helsinki-nlp,whisper}, --translation_recipe {helsinki-nlp,whisper}
+                        LLM recipe used for translating subtitles
+  -tf TRANSLATION_FLAVOUR, --translation_flavour TRANSLATION_FLAVOUR
+                        Flavour variation for a specific LLM recipe supporting translation
   -lgs, --languages     Print out language codes used for stretch and translation
   -d, --debug           Print out debugging information
   -q, --quiet           Switch off logging information
@@ -152,21 +157,40 @@ def main():
         choices=Utils.get_stretch_language_codes(),
         help="Target video's main language as an ISO 639-3 language code [https://en.wikipedia.org/wiki/List_of_ISO_639-3_codes]",
     )
+    from subaligner.llm import TranscriptionRecipe
+    from subaligner.llm import WhisperFlavour
     parser.add_argument(
         "-mr",
         "--llm_recipe",
         type=str.lower,
-        default="whisper",
-        choices=["whisper"],
+        default=TranscriptionRecipe.WHISPER.value,
+        choices=[r.value for r in TranscriptionRecipe],
         help="LLM recipe used for transcribing video files"
     )
     parser.add_argument(
         "-mf",
         "--llm_flavour",
         type=str.lower,
-        default="small",
-        choices=["tiny", "tiny.en", "small", "medium", "medium.en", "base", "base.en", "large-v1", "large-v2", "large"],
-        help="Flavour variation for a specific LLM recipe"
+        default=WhisperFlavour.SMALL.value,
+        choices=[wf.value for wf in WhisperFlavour],
+        help="Flavour variation for a specific LLM recipe supporting transcription"
+    )
+    from subaligner.llm import TranslationRecipe
+    from subaligner.llm import HelsinkiNLPFlavour
+    parser.add_argument(
+        "-tr",
+        "--translation_recipe",
+        type=str.lower,
+        default=TranslationRecipe.HELSINKI_NLP.value,
+        choices=[r.value for r in TranslationRecipe],
+        help="LLM recipe used for translating subtitles"
+    )
+    parser.add_argument(
+        "-tf",
+        "--translation_flavour",
+        type=str.lower,
+        default=None,
+        help="Flavour variation for a specific LLM recipe supporting translation"
     )
     parser.add_argument("-lgs", "--languages", action="store_true",
                         help="Print out language codes used for stretch and translation")
@@ -312,8 +336,8 @@ def main():
                 if FLAGS.translate is not None:
                     from subaligner.translator import Translator
                     source, target = FLAGS.translate.split(",")
-                    translator = Translator(source, target)
-                    aligned_subs = translator.translate(aligned_subs)
+                    translator = Translator(src_language=source, tgt_language=target, recipe=FLAGS.translation_recipe, flavour=FLAGS.translation_flavour)
+                    aligned_subs = translator.translate(aligned_subs, local_video_path)
                     Subtitle.save_subs_as_target_format(aligned_subs, local_subtitle_path, aligned_subtitle_path,
                                                         frame_rate, "utf-8")
                 elif FLAGS.mode == "transcribe":

diff --git a/subaligner/_version.py b/subaligner/_version.py
@@ -1,2 +1,2 @@
 """The semver for the current release."""
-__version__ = "0.3.0"
+__version__ = "0.3.1"
diff --git a/subaligner/exception.py b/subaligner/exception.py
@@ -10,5 +10,9 @@ class NoFrameRateException(Exception):
     """ An exception raised due to frame rate not found."""
 
 
+class TranslationException(Exception):
+    """ An exception raised due to translation failures."""
+
+
 class TranscriptionException(Exception):
     """ An exception raised due to transcription failures."""
diff --git a/subaligner/llm.py b/subaligner/llm.py
@@ -0,0 +1,29 @@
+from enum import Enum
+
+
+class TranscriptionRecipe(Enum):
+    WHISPER = "whisper"
+
+
+class TranslationRecipe(Enum):
+    HELSINKI_NLP = "helsinki-nlp"
+    WHISPER = "whisper"
+
+
+class WhisperFlavour(Enum):
+    TINY = "tiny"
+    TINY_EN = "tiny.en"
+    SMALL = "small"
+    MEDIUM = "medium"
+    MEDIUM_EN = "medium.en"
+    BASE = "base"
+    BASE_EN = "base.en"
+    LARGE_V1 = "large-v1"
+    LARGE_V2 = "large-v2"
+    LARGE = "large"
+
+
+class HelsinkiNLPFlavour(Enum):
+    OPUS_MT = "Helsinki-NLP/opus-mt-{}-{}"
+    OPUS_MT_TC_BIG = "Helsinki-NLP/opus-mt-tc-big-{}-{}"
+    OPUS_TATOEBA = "Helsinki-NLP/opus-tatoeba-{}-{}"