lattifai-captions 0.1.4__tar.gz

lattifai_captions-0.1.4/PKG-INFO

@@ -0,0 +1,292 @@
+Metadata-Version: 2.4
+Name: lattifai-captions
+Version: 0.1.4
+Summary: Caption/subtitle processing library with multi-format support (SRT, VTT, ASS, TTML, TextGrid, NLE formats)
+Author-email: LattifAI Technologies <tech@lattifai.com>
+Maintainer-email: Lattice <tech@lattifai.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/lattifai/captions
+Project-URL: Documentation, https://github.com/lattifai/captions/blob/main/README.md
+Project-URL: Bug Tracker, https://github.com/lattifai/captions/issues
+Keywords: captions,subtitles,srt,vtt,ass,ttml,textgrid,forced alignment
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Text Processing
+Requires-Python: <3.15,>=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pysubs2>=1.6.0
+Requires-Dist: praatio>=6.0.0
+Requires-Dist: tgt>=1.4.0
+Provides-Extra: splitting
+Requires-Dist: wtpsplit>=2.1.7; extra == "splitting"
+Requires-Dist: onnxruntime; extra == "splitting"
+Requires-Dist: huggingface_hub>=0.20.0; extra == "splitting"
+Requires-Dist: modelscope>=1.33.0; extra == "splitting"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: wtpsplit>=2.1.7; extra == "dev"
+Requires-Dist: onnxruntime; extra == "dev"
+Requires-Dist: huggingface_hub>=0.20.0; extra == "dev"
+Requires-Dist: modelscope>=1.33.0; extra == "dev"
+
+# lattifai-captions
+
+Caption/subtitle processing library with comprehensive format support.
+
+## Features
+
+- **Multi-format support**: SRT, VTT, ASS, SSA, TTML, TextGrid, LRC, SRV3, and more
+- **YouTube formats**: SRV3 (YTT v3), YouTube VTT with word-level timestamps
+- **Professional NLE formats**: Avid DS, Final Cut Pro XML, Premiere Pro XML, Adobe Audition
+- **Word-level timing**: Karaoke-style word-by-word timestamps
+- **Standardization**: Netflix/BBC broadcast guidelines compliance
+- **Sentence splitting**: AI-powered intelligent sentence segmentation
+- **Zero dependencies on heavy ML frameworks**: Lightweight and fast
+
+## Installation
+
+```bash
+# Basic installation
+pip install lattifai-captions
+
+# With sentence splitting support
+pip install lattifai-captions[splitting]
+```
+
+## Quick Start
+
+```python
+from lattifai.caption import Caption
+
+# Read a caption file
+caption = Caption.read("input.srt")
+
+# Write to different format
+caption.write("output.vtt")
+
+# Convert to string
+vtt_content = caption.to_string("vtt")
+
+# Access segments
+for segment in caption.supervisions:
+    print(f"{segment.start:.2f} - {segment.end:.2f}: {segment.text}")
+```
+
+## Supported Formats
+
+### Input/Output (Read & Write)
+
+| Format | Extensions | Description |
+|--------|------------|-------------|
+| **SRT** | `.srt` | SubRip subtitle format |
+| **VTT** | `.vtt` | WebVTT, includes YouTube VTT with word-level timestamps |
+| **ASS/SSA** | `.ass`, `.ssa` | Advanced SubStation Alpha |
+| **SRV3** | `.srv3`, `.ytt` | YouTube Timed Text v3 with word-level timing |
+| **SBV** | `.sbv` | YouTube SubViewer format |
+| **SUB** | `.sub` | MicroDVD subtitle format |
+| **SAMI** | `.sami`, `.smi` | SAMI subtitle format |
+| **JSON** | `.json` | Structured data with word-level support |
+| **CSV/TSV** | `.csv`, `.tsv` | Tabular formats |
+| **TextGrid** | `.textgrid` | Praat TextGrid format |
+| **LRC** | `.lrc` | Lyrics format with word-level timestamps |
+| **Gemini** | `.md` | Gemini AI transcript markdown |
+
+### Output Only
+
+| Format | Extensions | Description |
+|--------|------------|-------------|
+| **TTML** | `.ttml` | Timed Text Markup Language (W3C standard) |
+| **IMSC1** | `.ttml` | Netflix/streaming TTML profile |
+| **EBU-TT-D** | `.ttml` | European broadcast TTML profile |
+| **Avid DS** | `.txt` | Avid Media Composer SubCap |
+| **FCPXML** | `.fcpxml` | Final Cut Pro XML |
+| **Premiere XML** | `.xml` | Adobe Premiere Pro XML |
+| **Audition CSV** | `.csv` | Adobe Audition markers |
+| **EdiMarker CSV** | `.csv` | Pro Tools markers |
+
+## Word-Level Timing
+
+Many formats support word-level timing for karaoke-style output:
+
+```python
+from lattifai.caption import Caption
+
+caption = Caption.read("input.srv3")  # SRV3 has built-in word timing
+
+# Access word-level alignment
+for segment in caption.supervisions:
+    if segment.alignment and "word" in segment.alignment:
+        for word in segment.alignment["word"]:
+            print(f"  {word.symbol}: {word.start:.3f}s - {word.end:.3f}s")
+
+# Export with word-level timing
+caption.write("output.json", word_level=True)  # JSON preserves words array
+caption.write("output.ass", word_level=True, karaoke_config=KaraokeConfig(enabled=True))
+```
+
+## YouTube SRV3 Format
+
+SRV3 is YouTube's proprietary timed text format with millisecond-precision word timing:
+
+```python
+from lattifai.caption import Caption
+
+# Read SRV3 (automatically extracts word-level timing)
+caption = Caption.read("video.srv3")
+
+# Convert to other formats
+caption.write("output.srt")  # Standard SRT
+caption.write("output.vtt", word_level=True)  # VTT with word timing
+caption.write("output.srv3", word_level=True)  # Back to SRV3
+```
+
+SRV3 structure example:
+```xml
+<timedtext format="3">
+  <body>
+    <p t="240" d="6559" w="1">
+      <s ac="0">Does</s>
+      <s t="320" ac="0"> fast</s>
+      <s t="560" ac="0"> charging</s>
+    </p>
+  </body>
+</timedtext>
+```
+
+## Sentence Splitting
+
+Split captions into natural sentences (requires `[splitting]` extra):
+
+```python
+from lattifai.caption import Caption, SentenceSplitter
+
+# Using Caption method
+caption = Caption.read("input.srt")
+split_caption = caption.split_sentences()
+
+# Or use SentenceSplitter directly
+splitter = SentenceSplitter()
+split_supervisions = splitter.split_sentences(caption.supervisions)
+```
+
+## Format Conversion
+
+```python
+from lattifai.caption import Caption
+
+# Read any format
+caption = Caption.read("input.srt")
+
+# Write to any supported format
+caption.write("output.vtt")
+caption.write("output.ass")
+caption.write("output.json")
+caption.write("output.srv3", word_level=True)
+caption.write("output.ttml")
+
+# Or get as string
+srt_content = caption.to_string("srt")
+json_content = caption.to_string("json", word_level=True)
+```
+
+## Standardization
+
+Apply broadcast standards to captions:
+
+```python
+from lattifai.caption import Caption, CaptionStandardizer
+
+standardizer = CaptionStandardizer(
+    min_duration=0.7,      # Minimum segment duration
+    max_duration=7.0,      # Maximum segment duration
+    min_gap=0.08,          # Minimum gap between segments
+    max_lines=2,           # Maximum lines per segment
+    max_chars_per_line=42, # Maximum characters per line
+)
+
+caption = Caption.read("input.srt")
+standardized = standardizer.process(caption.supervisions)
+```
+
+## Validation
+
+Check captions against quality standards:
+
+```python
+from lattifai.caption import Caption, CaptionValidator
+
+validator = CaptionValidator(
+    min_duration=0.7,
+    max_duration=7.0,
+    min_gap=0.08,
+    max_chars_per_line=42,
+)
+
+caption = Caption.read("input.srt")
+result = validator.validate(caption.supervisions)
+
+print(f"Valid: {result.valid}")
+print(f"Average CPS: {result.avg_cps:.1f}")
+print(f"Max CPL: {result.max_cpl}")
+print(f"Warnings: {result.warnings}")
+```
+
+## API Reference
+
+### Caption Class
+
+```python
+from lattifai.caption import Caption
+
+# Class methods
+Caption.read(path, format=None, normalize_text=True)
+Caption.from_string(content, format)
+Caption.from_supervisions(supervisions, language=None, metadata=None)
+
+# Instance methods
+caption.write(path, include_speaker=True, word_level=False, karaoke_config=None)
+caption.to_string(format, include_speaker=True, word_level=False, karaoke_config=None)
+caption.split_sentences()
+caption.shift_time(seconds)
+
+# Properties
+caption.supervisions  # List[Supervision]
+caption.duration      # Total duration in seconds
+caption.language      # Language code
+caption.source_format # Original format
+```
+
+### Supervision Class
+
+```python
+from lattifai.caption import Supervision
+
+sup = Supervision(
+    start=0.0,           # Start time in seconds
+    duration=2.5,        # Duration in seconds
+    text="Hello world",  # Caption text
+    speaker="Alice",     # Optional speaker label
+    alignment=None,      # Optional word-level alignment
+)
+
+# Properties
+sup.end       # start + duration
+sup.text      # Caption text
+sup.speaker   # Speaker label
+sup.alignment # Dict with "word" key containing AlignmentItem list
+```
+
+## License
+
+Apache-2.0

lattifai_captions-0.1.4/README.md

@@ -0,0 +1,250 @@
+# lattifai-captions
+
+Caption/subtitle processing library with comprehensive format support.
+
+## Features
+
+- **Multi-format support**: SRT, VTT, ASS, SSA, TTML, TextGrid, LRC, SRV3, and more
+- **YouTube formats**: SRV3 (YTT v3), YouTube VTT with word-level timestamps
+- **Professional NLE formats**: Avid DS, Final Cut Pro XML, Premiere Pro XML, Adobe Audition
+- **Word-level timing**: Karaoke-style word-by-word timestamps
+- **Standardization**: Netflix/BBC broadcast guidelines compliance
+- **Sentence splitting**: AI-powered intelligent sentence segmentation
+- **Zero dependencies on heavy ML frameworks**: Lightweight and fast
+
+## Installation
+
+```bash
+# Basic installation
+pip install lattifai-captions
+
+# With sentence splitting support
+pip install lattifai-captions[splitting]
+```
+
+## Quick Start
+
+```python
+from lattifai.caption import Caption
+
+# Read a caption file
+caption = Caption.read("input.srt")
+
+# Write to different format
+caption.write("output.vtt")
+
+# Convert to string
+vtt_content = caption.to_string("vtt")
+
+# Access segments
+for segment in caption.supervisions:
+    print(f"{segment.start:.2f} - {segment.end:.2f}: {segment.text}")
+```
+
+## Supported Formats
+
+### Input/Output (Read & Write)
+
+| Format | Extensions | Description |
+|--------|------------|-------------|
+| **SRT** | `.srt` | SubRip subtitle format |
+| **VTT** | `.vtt` | WebVTT, includes YouTube VTT with word-level timestamps |
+| **ASS/SSA** | `.ass`, `.ssa` | Advanced SubStation Alpha |
+| **SRV3** | `.srv3`, `.ytt` | YouTube Timed Text v3 with word-level timing |
+| **SBV** | `.sbv` | YouTube SubViewer format |
+| **SUB** | `.sub` | MicroDVD subtitle format |
+| **SAMI** | `.sami`, `.smi` | SAMI subtitle format |
+| **JSON** | `.json` | Structured data with word-level support |
+| **CSV/TSV** | `.csv`, `.tsv` | Tabular formats |
+| **TextGrid** | `.textgrid` | Praat TextGrid format |
+| **LRC** | `.lrc` | Lyrics format with word-level timestamps |
+| **Gemini** | `.md` | Gemini AI transcript markdown |
+
+### Output Only
+
+| Format | Extensions | Description |
+|--------|------------|-------------|
+| **TTML** | `.ttml` | Timed Text Markup Language (W3C standard) |
+| **IMSC1** | `.ttml` | Netflix/streaming TTML profile |
+| **EBU-TT-D** | `.ttml` | European broadcast TTML profile |
+| **Avid DS** | `.txt` | Avid Media Composer SubCap |
+| **FCPXML** | `.fcpxml` | Final Cut Pro XML |
+| **Premiere XML** | `.xml` | Adobe Premiere Pro XML |
+| **Audition CSV** | `.csv` | Adobe Audition markers |
+| **EdiMarker CSV** | `.csv` | Pro Tools markers |
+
+## Word-Level Timing
+
+Many formats support word-level timing for karaoke-style output:
+
+```python
+from lattifai.caption import Caption
+
+caption = Caption.read("input.srv3")  # SRV3 has built-in word timing
+
+# Access word-level alignment
+for segment in caption.supervisions:
+    if segment.alignment and "word" in segment.alignment:
+        for word in segment.alignment["word"]:
+            print(f"  {word.symbol}: {word.start:.3f}s - {word.end:.3f}s")
+
+# Export with word-level timing
+caption.write("output.json", word_level=True)  # JSON preserves words array
+caption.write("output.ass", word_level=True, karaoke_config=KaraokeConfig(enabled=True))
+```
+
+## YouTube SRV3 Format
+
+SRV3 is YouTube's proprietary timed text format with millisecond-precision word timing:
+
+```python
+from lattifai.caption import Caption
+
+# Read SRV3 (automatically extracts word-level timing)
+caption = Caption.read("video.srv3")
+
+# Convert to other formats
+caption.write("output.srt")  # Standard SRT
+caption.write("output.vtt", word_level=True)  # VTT with word timing
+caption.write("output.srv3", word_level=True)  # Back to SRV3
+```
+
+SRV3 structure example:
+```xml
+<timedtext format="3">
+  <body>
+    <p t="240" d="6559" w="1">
+      <s ac="0">Does</s>
+      <s t="320" ac="0"> fast</s>
+      <s t="560" ac="0"> charging</s>
+    </p>
+  </body>
+</timedtext>
+```
+
+## Sentence Splitting
+
+Split captions into natural sentences (requires `[splitting]` extra):
+
+```python
+from lattifai.caption import Caption, SentenceSplitter
+
+# Using Caption method
+caption = Caption.read("input.srt")
+split_caption = caption.split_sentences()
+
+# Or use SentenceSplitter directly
+splitter = SentenceSplitter()
+split_supervisions = splitter.split_sentences(caption.supervisions)
+```
+
+## Format Conversion
+
+```python
+from lattifai.caption import Caption
+
+# Read any format
+caption = Caption.read("input.srt")
+
+# Write to any supported format
+caption.write("output.vtt")
+caption.write("output.ass")
+caption.write("output.json")
+caption.write("output.srv3", word_level=True)
+caption.write("output.ttml")
+
+# Or get as string
+srt_content = caption.to_string("srt")
+json_content = caption.to_string("json", word_level=True)
+```
+
+## Standardization
+
+Apply broadcast standards to captions:
+
+```python
+from lattifai.caption import Caption, CaptionStandardizer
+
+standardizer = CaptionStandardizer(
+    min_duration=0.7,      # Minimum segment duration
+    max_duration=7.0,      # Maximum segment duration
+    min_gap=0.08,          # Minimum gap between segments
+    max_lines=2,           # Maximum lines per segment
+    max_chars_per_line=42, # Maximum characters per line
+)
+
+caption = Caption.read("input.srt")
+standardized = standardizer.process(caption.supervisions)
+```
+
+## Validation
+
+Check captions against quality standards:
+
+```python
+from lattifai.caption import Caption, CaptionValidator
+
+validator = CaptionValidator(
+    min_duration=0.7,
+    max_duration=7.0,
+    min_gap=0.08,
+    max_chars_per_line=42,
+)
+
+caption = Caption.read("input.srt")
+result = validator.validate(caption.supervisions)
+
+print(f"Valid: {result.valid}")
+print(f"Average CPS: {result.avg_cps:.1f}")
+print(f"Max CPL: {result.max_cpl}")
+print(f"Warnings: {result.warnings}")
+```
+
+## API Reference
+
+### Caption Class
+
+```python
+from lattifai.caption import Caption
+
+# Class methods
+Caption.read(path, format=None, normalize_text=True)
+Caption.from_string(content, format)
+Caption.from_supervisions(supervisions, language=None, metadata=None)
+
+# Instance methods
+caption.write(path, include_speaker=True, word_level=False, karaoke_config=None)
+caption.to_string(format, include_speaker=True, word_level=False, karaoke_config=None)
+caption.split_sentences()
+caption.shift_time(seconds)
+
+# Properties
+caption.supervisions  # List[Supervision]
+caption.duration      # Total duration in seconds
+caption.language      # Language code
+caption.source_format # Original format
+```
+
+### Supervision Class
+
+```python
+from lattifai.caption import Supervision
+
+sup = Supervision(
+    start=0.0,           # Start time in seconds
+    duration=2.5,        # Duration in seconds
+    text="Hello world",  # Caption text
+    speaker="Alice",     # Optional speaker label
+    alignment=None,      # Optional word-level alignment
+)
+
+# Properties
+sup.end       # start + duration
+sup.text      # Caption text
+sup.speaker   # Speaker label
+sup.alignment # Dict with "word" key containing AlignmentItem list
+```
+
+## License
+
+Apache-2.0

lattifai_captions-0.1.4/pyproject.toml

@@ -0,0 +1,72 @@
+[build-system]
+requires = ['setuptools>=60,<80', 'wheel']
+build-backend = 'setuptools.build_meta'
+
+[project]
+name = 'lattifai-captions'
+version = '0.1.4'
+description = "Caption/subtitle processing library with multi-format support (SRT, VTT, ASS, TTML, TextGrid, NLE formats)"
+keywords = ['captions', 'subtitles', 'srt', 'vtt', 'ass', 'ttml', 'textgrid', 'forced alignment']
+readme = 'README.md'
+license = {text = 'Apache-2.0'}
+authors = [
+  { name = 'LattifAI Technologies', email = 'tech@lattifai.com' },
+]
+maintainers = [
+  { name = 'Lattice', email = 'tech@lattifai.com' },
+]
+requires-python = '>=3.10,<3.15'
+
+classifiers = [
+    'Development Status :: 4 - Beta',
+    'Intended Audience :: Developers',
+    'Intended Audience :: Science/Research',
+    'License :: OSI Approved :: Apache Software License',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
+    'Programming Language :: Python :: 3.13',
+    'Programming Language :: Python :: 3.14',
+    'Operating System :: OS Independent',
+    'Topic :: Multimedia :: Sound/Audio',
+    'Topic :: Multimedia :: Video',
+    'Topic :: Text Processing',
+]
+
+dependencies = [
+    "pysubs2>=1.6.0",
+    "praatio>=6.0.0",
+    "tgt>=1.4.0",
+]
+
+[project.optional-dependencies]
+splitting = [
+    "wtpsplit>=2.1.7",
+    "onnxruntime",
+    "huggingface_hub>=0.20.0",
+    "modelscope>=1.33.0",
+]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-cov>=4.1.0",
+    "wtpsplit>=2.1.7",
+    "onnxruntime",
+    "huggingface_hub>=0.20.0",
+    "modelscope>=1.33.0",
+]
+
+[project.urls]
+Homepage = 'https://github.com/lattifai/captions'
+Documentation = 'https://github.com/lattifai/captions/blob/main/README.md'
+'Bug Tracker' = 'https://github.com/lattifai/captions/issues'
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = true
+
+[tool.setuptools.package-dir]
+"" = "src"
+
+[tool.pytest.ini_options]
+addopts = "--durations=10"
+testpaths = ["tests"]

lattifai_captions-0.1.4/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+