lattifai 1.0.4__py3-none-any.whl → 1.1.0__py3-none-any.whl

lattifai/utils.py

@@ -1,13 +1,49 @@
 """Shared utility helpers for the LattifAI SDK."""
 
-import os
+import sys
 from datetime import datetime, timedelta
 from pathlib import Path
-from typing import Any, Optional, Type
+from typing import Optional
 
 from lattifai.errors import ModelLoadError
 
 
+def safe_print(text: str, **kwargs) -> None:
+    """
+    Safely print text with Unicode characters, handling Windows encoding issues.
+
+    On Windows, the default console encoding (cp1252) can't handle many Unicode
+    characters like emojis. This function ensures text is printed correctly by
+    using UTF-8 encoding when necessary.
+
+    Args:
+        text: The text to print, may contain Unicode/emoji characters
+        **kwargs: Additional arguments passed to print()
+    """
+    try:
+        print(text, **kwargs)
+    except UnicodeEncodeError:
+        # On Windows, try to reconfigure stdout to use UTF-8
+        if sys.platform == "win32":
+            try:
+                # Try to encode with UTF-8 and print
+                if hasattr(sys.stdout, "buffer"):
+                    sys.stdout.buffer.write((text + "\n").encode("utf-8"))
+                    sys.stdout.flush()
+                else:
+                    # Fallback: replace problematic characters
+                    print(text.encode(sys.stdout.encoding, errors="replace").decode(sys.stdout.encoding), **kwargs)
+            except Exception:
+                # Last resort: remove emojis
+                import re
+
+                text_no_emoji = re.sub(r"[^\x00-\x7F\u4e00-\u9fff]+", "", text)
+                print(text_no_emoji, **kwargs)
+        else:
+            # Non-Windows: this shouldn't happen, but fallback gracefully
+            print(text.encode("utf-8", errors="replace").decode("utf-8"), **kwargs)
+
+
 def _get_cache_marker_path(cache_dir: Path) -> Path:
     """Get the path for the cache marker file with current date."""
     today = datetime.now().strftime("%Y%m%d")
@@ -51,42 +87,74 @@ def _create_cache_marker(cache_dir: Path) -> None:
     marker_path.touch()
 
 
-def _resolve_model_path(model_name_or_path: str) -> str:
-    """Resolve model path, downloading from Hugging Face when necessary."""
+def _resolve_model_path(model_name_or_path: str, model_hub: str = "huggingface") -> str:
+    """Resolve model path, downloading from the specified model hub when necessary.
+
+    Args:
+        model_name_or_path: Local path or remote model identifier.
+        model_hub: Which hub to use for downloads. Supported: "huggingface", "modelscope".
+    """
     if Path(model_name_or_path).expanduser().exists():
         return str(Path(model_name_or_path).expanduser())
 
-    from huggingface_hub import snapshot_download
-    from huggingface_hub.constants import HF_HUB_CACHE
-    from huggingface_hub.errors import LocalEntryNotFoundError
+    # Normalize hub name
+    hub = (model_hub or "huggingface").lower()
 
-    # Determine cache directory for this model
-    cache_dir = Path(HF_HUB_CACHE) / f'models--{model_name_or_path.replace("/", "--")}'
+    if hub not in ("huggingface", "modelscope"):
+        raise ValueError(f"Unsupported model_hub: {model_hub}. Supported: 'huggingface', 'modelscope'.")
+
+    # If local path exists, return it regardless of hub
+    if Path(model_name_or_path).expanduser().exists():
+        return str(Path(model_name_or_path).expanduser())
 
-    # Check if we have a valid cached version
-    if _is_cache_valid(cache_dir):
-        # Return the snapshot path (latest version)
-        snapshots_dir = cache_dir / "snapshots"
-        if snapshots_dir.exists():
-            snapshot_dirs = [d for d in snapshots_dir.iterdir() if d.is_dir()]
-            if snapshot_dirs:
-                # Return the most recent snapshot
-                latest_snapshot = max(snapshot_dirs, key=lambda p: p.stat().st_mtime)
-                return str(latest_snapshot)
+    if hub == "huggingface":
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.constants import HF_HUB_CACHE
+        from huggingface_hub.errors import LocalEntryNotFoundError
+
+        # Determine cache directory for this model
+        cache_dir = Path(HF_HUB_CACHE) / f'models--{model_name_or_path.replace("/", "--")}'
+
+        # Check if we have a valid cached version
+        if _is_cache_valid(cache_dir):
+            # Return the snapshot path (latest version)
+            snapshots_dir = cache_dir / "snapshots"
+            if snapshots_dir.exists():
+                snapshot_dirs = [d for d in snapshots_dir.iterdir() if d.is_dir()]
+                if snapshot_dirs:
+                    # Return the most recent snapshot
+                    latest_snapshot = max(snapshot_dirs, key=lambda p: p.stat().st_mtime)
+                    return str(latest_snapshot)
 
-    try:
-        downloaded_path = snapshot_download(repo_id=model_name_or_path, repo_type="model")
-        _create_cache_marker(cache_dir)
-        return downloaded_path
-    except LocalEntryNotFoundError:
         try:
-            os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
             downloaded_path = snapshot_download(repo_id=model_name_or_path, repo_type="model")
             _create_cache_marker(cache_dir)
             return downloaded_path
-        except Exception as e:  # pragma: no cover - bubble up for caller context
-            raise ModelLoadError(model_name_or_path, original_error=e)
-    except Exception as e:  # pragma: no cover - unexpected download issue
+        except LocalEntryNotFoundError:
+            # Fall back to modelscope if HF entry not found
+            try:
+                from modelscope.hub.snapshot_download import snapshot_download as ms_snapshot
+
+                downloaded_path = ms_snapshot(model_name_or_path)
+                return downloaded_path
+            except Exception as e:  # pragma: no cover - bubble up for caller context
+                raise ModelLoadError(model_name_or_path, original_error=e)
+        except Exception as e:  # pragma: no cover - unexpected download issue
+            import colorful
+
+            print(colorful.red | f"Error downloading from Hugging Face Hub: {e}. Trying ModelScope...")
+            from modelscope.hub.snapshot_download import snapshot_download as ms_snapshot
+
+            downloaded_path = ms_snapshot(model_name_or_path)
+            return downloaded_path
+
+    # modelscope path
+    from modelscope.hub.snapshot_download import snapshot_download as ms_snapshot
+
+    try:
+        downloaded_path = ms_snapshot(model_name_or_path)
+        return downloaded_path
+    except Exception as e:  # pragma: no cover
         raise ModelLoadError(model_name_or_path, original_error=e)
 
 

lattifai/workflow/file_manager.py

@@ -1,4 +1,4 @@
-"""
+""".
 File existence management utilities for video processing workflows
 """
 
@@ -11,6 +11,8 @@ from typing import Dict, List, Optional, Sequence, Tuple
 
 import colorful
 
+from lattifai.utils import safe_print
+
 try:
     import questionary
 except ImportError:  # pragma: no cover - optional dependency
@@ -110,7 +112,7 @@ class FileExistenceManager:
             return "proceed"  # No existing files, proceed normally
 
         # Header with warning color
-        print(f'\n{colorful.bold_yellow("⚠️  Existing files found:")}')
+        safe_print(f'\n{colorful.bold_yellow("⚠️  Existing files found:")}')
 
         # Collect file paths for options
         file_paths = []
@@ -157,15 +159,15 @@ class FileExistenceManager:
         choice = FileExistenceManager._prompt_user_choice(prompt_message, options, default=default_value)
 
         if choice == "overwrite":
-            print(f'{colorful.yellow("🔄 Overwriting existing files")}')
+            safe_print(f'{colorful.yellow("🔄 Overwriting existing files")}')
         elif choice == TRANSCRIBE_CHOICE:
             print(f'{colorful.magenta(f"✨ Will transcribe with {transcriber_name}")}')
         elif choice == "cancel":
-            print(f'{colorful.red("❌ Operation cancelled")}')
+            safe_print(f'{colorful.red("❌ Operation cancelled")}')
         elif choice in file_paths:
-            print(f'{colorful.green(f"✅ Using selected file: {choice}")}')
+            safe_print(f'{colorful.green(f"✅ Using selected file: {choice}")}')
         else:
-            print(f'{colorful.green("✅ Using existing files")}')
+            safe_print(f'{colorful.green("✅ Using existing files")}')
 
         return choice
 
@@ -189,7 +191,7 @@ class FileExistenceManager:
         del emoji  # Unused variable
 
         # Header with warning color
-        print(f'\n{colorful.bold_yellow(f"⚠️  Existing {label} files found:")}')
+        safe_print(f'\n{colorful.bold_yellow(f"⚠️  Existing {label} files found:")}')
 
         for file_path in sorted(files):
             print(f'   {colorful.green("•")} {file_path}')
@@ -203,11 +205,11 @@ class FileExistenceManager:
         choice = FileExistenceManager._prompt_user_choice(prompt_message, options, default="use")
 
         if choice == "use":
-            print(f'{colorful.green(f"✅ Using existing {label} files")}')
+            safe_print(f'{colorful.green(f"✅ Using existing {label} files")}')
         elif choice == "overwrite":
-            print(f'{colorful.yellow(f"🔄 Overwriting {label} files")}')
+            safe_print(f'{colorful.yellow(f"🔄 Overwriting {label} files")}')
         elif choice == "cancel":
-            print(f'{colorful.red("❌ Operation cancelled")}')
+            safe_print(f'{colorful.red("❌ Operation cancelled")}')
 
         return choice
 
@@ -245,7 +247,7 @@ class FileExistenceManager:
             )
 
         # Multiple files: let user choose which one
-        print(f'\n{colorful.bold_yellow(f"⚠️  Multiple {file_type} files found:")}')
+        safe_print(f'\n{colorful.bold_yellow(f"⚠️  Multiple {file_type} files found:")}')
 
         # Create options with full file paths
         options = []
@@ -266,7 +268,7 @@ class FileExistenceManager:
         choice = FileExistenceManager._prompt_user_choice(prompt_message, options, default=files[0])
 
         if choice == "cancel":
-            print(f'{colorful.red("❌ Operation cancelled")}')
+            safe_print(f'{colorful.red("❌ Operation cancelled")}')
         elif choice == "overwrite":
             overwrite_msg = f"🔄 Overwriting all {file_type} files"
             print(f"{colorful.yellow(overwrite_msg)}")
@@ -274,7 +276,7 @@ class FileExistenceManager:
             transcribe_msg = f"✨ Will transcribe with {transcriber_name}"
             print(f"{colorful.magenta(transcribe_msg)}")
         else:
-            print(f'{colorful.green(f"✅ Using: {choice}")}')
+            safe_print(f'{colorful.green(f"✅ Using: {choice}")}')
 
         return choice
 

lattifai/workflow/youtube.py

@@ -407,6 +407,11 @@ class YouTubeDownloader:
             output_template,
             "--sub-format",
             "best",  # Prefer best available format
+            "--no-warnings",  # Suppress warnings for cleaner output
+            "--extractor-retries",
+            "3",  # Retry on errors
+            "--sleep-requests",
+            "1",  # Sleep between requests to avoid rate limiting
         ]
 
         # Add caption language selection if specified
@@ -425,7 +430,8 @@ class YouTubeDownloader:
                 None, lambda: subprocess.run(ytdlp_options, capture_output=True, text=True, check=True)
             )
 
-            self.logger.info(f"yt-dlp transcript output: {result.stdout.strip()}")
+            # Only log success message, not full yt-dlp output
+            self.logger.debug(f"yt-dlp output: {result.stdout.strip()}")
 
             # Find the downloaded transcript file
             caption_patterns = [
@@ -481,9 +487,18 @@ class YouTubeDownloader:
 
         except subprocess.CalledProcessError as e:
             error_msg = e.stderr.strip() if e.stderr else str(e)
+
+            # Check for specific error conditions
             if "No automatic or manual captions found" in error_msg:
                 self.logger.warning("No captions available for this video")
                 return None
+            elif "HTTP Error 429" in error_msg or "Too Many Requests" in error_msg:
+                self.logger.error("YouTube rate limit exceeded. Please try again later or use a different method.")
+                raise RuntimeError(
+                    "YouTube rate limit exceeded (HTTP 429). "
+                    "Try again later or use --cookies option with authenticated cookies. "
+                    "See: https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp"
+                )
             else:
                 self.logger.error(f"Failed to download transcript: {error_msg}")
                 raise RuntimeError(f"Failed to download transcript: {error_msg}")

{lattifai-1.0.4.dist-info → lattifai-1.1.0.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: lattifai
-Version: 1.0.4
+Version: 1.1.0
 Summary: Lattifai Python SDK: Seamless Integration with Lattifai's Speech and Video AI Services
 Author-email: Lattifai Technologies <tech@lattifai.com>
 Maintainer-email: Lattice <tech@lattifai.com>
 License: MIT License
         
-        Copyright (c) 2025 Lattifai.
+        Copyright (c) 2025 LattifAI.
         
         Permission is hereby granted, free of charge, to any person obtaining a copy
         of this software and associated documentation files (the "Software"), to deal
@@ -27,10 +27,10 @@ License: MIT License
         SOFTWARE.
         
 Project-URL: Homepage, https://github.com/lattifai/lattifai-python
-Project-URL: Documentation, https://github.com/lattifai/lattifai-python/README.md
+Project-URL: Documentation, https://github.com/lattifai/lattifai-python/blob/main/README.md
 Project-URL: Bug Tracker, https://github.com/lattifai/lattifai-python/issues
 Project-URL: Discussions, https://github.com/lattifai/lattifai-python/discussions
-Project-URL: Changelog, https://github.com/lattifai/lattifai-python/CHANGELOG.md
+Project-URL: Changelog, https://github.com/lattifai/lattifai-python/blob/main/CHANGELOG.md
 Keywords: lattifai,speech recognition,video analysis,ai,sdk,api client
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
@@ -50,7 +50,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: <3.15,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: lattifai-core>=0.4.6
+Requires-Dist: lattifai-core>=0.6.0
 Requires-Dist: lattifai-run>=1.0.1
 Requires-Dist: python-dotenv
 Requires-Dist: lhotse>=1.26.0
@@ -61,12 +61,12 @@ Requires-Dist: tgt
 Requires-Dist: onnx>=1.16.0
 Requires-Dist: onnxruntime
 Requires-Dist: msgpack
+Requires-Dist: scipy!=1.16.3
 Requires-Dist: g2p-phonemizer>=0.4.0
 Requires-Dist: av
-Requires-Dist: wtpsplit>=2.1.6
-Requires-Dist: kaldi-native-fbank
-Requires-Dist: OmniSenseVoice>=0.4.0
-Requires-Dist: nemo_toolkit_asr[asr]>=2.7.0rc1
+Requires-Dist: wtpsplit>=2.1.7
+Requires-Dist: OmniSenseVoice>=0.4.2
+Requires-Dist: nemo_toolkit_asr[asr]>=2.7.0rc4
 Requires-Dist: pyannote-audio-notorchdeps>=4.0.2
 Requires-Dist: questionary>=2.0
 Requires-Dist: yt-dlp
@@ -83,7 +83,7 @@ Requires-Dist: torch-audiomentations==0.12.0; extra == "diarization"
 Requires-Dist: pyannote.audio>=4.0.2; extra == "diarization"
 Provides-Extra: transcription
 Requires-Dist: OmniSenseVoice>=0.4.0; extra == "transcription"
-Requires-Dist: nemo_toolkit_asr[asr]>=2.7.0rc1; extra == "transcription"
+Requires-Dist: nemo_toolkit_asr[asr]>=2.7.0rc3; extra == "transcription"
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
@@ -114,10 +114,6 @@ Dynamic: license-file
 
 Advanced forced alignment and subtitle generation powered by [ 🤗 Lattice-1](https://huggingface.co/Lattifai/Lattice-1) model.
 
-> **⚠️ Note on Current Limitations**:
-> 1. **Memory Usage**: We are aware of high memory consumption and are actively working on further optimizations.
-> 2. **Long Audio**: Currently, long audio files might face issues. Support for **long-form audio (up to 20 hours)** will be available shortly.
-
 ## Table of Contents
 
 - [Installation](#installation)
@@ -138,7 +134,7 @@ Advanced forced alignment and subtitle generation powered by [ 🤗 Lattice-1](h
 - [Advanced Features](#advanced-features)
   - [Word-Level Alignment](#word-level-alignment)
   - [Smart Sentence Splitting](#smart-sentence-splitting)
-  - [Speaker Diarization](#speaker-diarization-wip)
+  - [Speaker Diarization](#speaker-diarization)
   - [YAML Configuration Files](#yaml-configuration-files)
 - [Supported Formats](#supported-formats)
 - [Roadmap](#roadmap)
@@ -464,6 +460,8 @@ lai transcribe align \
 
 ```bash
 lai caption convert input.srt output.vtt
+lai caption convert input.srt output.json
+# Enable normalization to clean HTML entities and special characters:
 lai caption convert input.srt output.json normalize_text=true
 ```
 
@@ -554,10 +552,10 @@ from lattifai import LattifAI, CaptionConfig
 
 client = LattifAI(
     caption_config=CaptionConfig(
-        split_sentence=True,           # Smart sentence splitting
-        word_level=True,               # Word-level timestamps
-        normalize_text=True,           # Clean HTML entities
-        include_speaker_in_text=False, # Include speaker labels
+        split_sentence=True,           # Smart sentence splitting (default: False)
+        word_level=True,               # Word-level timestamps (default: False)
+        normalize_text=True,           # Clean HTML entities (default: True)
+        include_speaker_in_text=False, # Include speaker labels (default: True)
     )
 )
 ```
@@ -619,6 +617,56 @@ from lattifai import (
 
 ## Advanced Features
 
+### Long-Form Audio Support
+
+LattifAI now supports processing long audio files (up to 20 hours) through streaming mode. Enable streaming by setting the `streaming_chunk_secs` parameter:
+
+**Python SDK:**
+```python
+from lattifai import LattifAI
+
+client = LattifAI()
+
+# Enable streaming for long audio files
+caption = client.alignment(
+    input_media="long_audio.wav",
+    input_caption="subtitle.srt",
+    output_caption_path="output.srt",
+    streaming_chunk_secs=600.0,  # Process in 30-second chunks
+)
+```
+
+**CLI:**
+```bash
+# Enable streaming with chunk size
+lai alignment align long_audio.wav subtitle.srt output.srt \
+    media.streaming_chunk_secs=300.0
+
+# For YouTube videos
+lai alignment youtube "https://youtube.com/watch?v=VIDEO_ID" \
+    media.streaming_chunk_secs=300.0
+```
+
+**MediaConfig:**
+```python
+from lattifai import LattifAI, MediaConfig
+
+client = LattifAI(
+    media_config=MediaConfig(
+        streaming_chunk_secs=600.0,  # Chunk duration in seconds (1-1800), default: 600 (10 minutes)
+    )
+)
+```
+
+**Notes:**
+- Chunk duration must be between 1 and 1800 seconds (minimum 1 second, maximum 30 minutes)
+- Default value: 600 seconds (10 minutes)
+- **Recommended: Use 60 seconds or larger for optimal performance**
+- Set to `None` to disable streaming
+- **Thanks to our precise implementation, streaming has virtually no impact on alignment accuracy**
+- Smaller chunks reduce memory usage with minimal quality trade-off
+- Recommended chunk size: 300-900 seconds (5-15 minutes) for optimal balance
+
 ### Word-Level Alignment
 
 Enable `word_level=True` to get precise timestamps for each word:
@@ -658,9 +706,7 @@ caption = client.alignment(
 )
 ```
 
-### Speaker Diarization (WIP)
-
-**Note:** This feature is currently under development and not yet fully available.
+### Speaker Diarization
 
 Speaker diarization automatically identifies and labels different speakers in audio. When enabled, the system will:
 - Detect speaker changes in the audio
@@ -671,6 +717,24 @@ Speaker diarization automatically identifies and labels different speakers in au
 - **Existing speaker labels in subtitles**: If your input captions already contain speaker names (e.g., `[Alice]`, `>> Bob:`, or `SPEAKER_01:`), the system will preserve them as much as possible during alignment
 - **Gemini Transcriber**: When using Gemini models for transcription (e.g., `gemini-2.5-pro`), the model can intelligently identify and extract speaker names from dialogue context, making it easier to generate speaker-aware transcripts
 
+**CLI:**
+```bash
+# Enable speaker diarization during alignment
+lai alignment align audio.wav subtitle.srt output.srt \
+    diarization.enabled=true
+
+# With additional diarization settings
+lai alignment align audio.wav subtitle.srt output.srt \
+    diarization.enabled=true \
+    diarization.device=cuda \
+    diarization.min_speakers=2 \
+    diarization.max_speakers=4
+
+# For YouTube videos with diarization
+lai alignment youtube "https://youtube.com/watch?v=VIDEO_ID" \
+    diarization.enabled=true
+```
+
 **Python SDK:**
 ```python
 from lattifai import LattifAI, DiarizationConfig

lattifai-1.1.0.dist-info/RECORD

@@ -0,0 +1,57 @@
+lattifai/__init__.py,sha256=7y1R5IGw0Sgvl1tfqxEK7e-ozW0wVB-q_JZgv6YyrMQ,2751
+lattifai/audio2.py,sha256=BKMCzkuEmBFAWOEnzgLxeK8TBPTFbjzr1esOfe3MQoo,17460
+lattifai/client.py,sha256=yD8yIcw3xfvPqBzUQTJj5h9sFYbg4BSHBR5gwO-wGF8,18875
+lattifai/errors.py,sha256=LyWRGVhQ6Ak2CYn9FBYAPRgQ7_VHpxzNsXI31HXD--s,11291
+lattifai/logging.py,sha256=MbUEeOUFlF92pA9v532DiPPWKl03S7UHCJ6Z652cf0w,2860
+lattifai/mixin.py,sha256=t8A3J1DVr7SBEv2FYK3JrGEFqxAV3NktfGPiOQdxTB4,24990
+lattifai/types.py,sha256=SjYBfwrCBOXlICvH04niFQJ7OzTx7oTaa_npfRkB67U,659
+lattifai/utils.py,sha256=N4k2cvoT2CgHsGY0sb-3l-eKUMLzGirPzVa53v8euh4,6658
+lattifai/alignment/__init__.py,sha256=ehpkKfjNIYUx7_M-RWD_8Efcrzd9bE-NSm0QgMMVLW0,178
+lattifai/alignment/lattice1_aligner.py,sha256=5c_bWv0v6jOX8H4gO3-mAKXn4Ux4vjHIUtAY4d8yMak,6110
+lattifai/alignment/lattice1_worker.py,sha256=U_EbDsbisWWKIyfxtx9q4deAyml_hni8DpznZo5zBko,12975
+lattifai/alignment/phonemizer.py,sha256=fbhN2DOl39lW4nQWKzyUUTMUabg7v61lB1kj8SKK-Sw,1761
+lattifai/alignment/segmenter.py,sha256=mzWEQC6hWZtI2mR2WU59W7qLHa7KXy7fdU6991kyUuQ,6276
+lattifai/alignment/tokenizer.py,sha256=GNLZbkvZ066PJGUznJVgxZUwSzslD6mz8YsI2Cry6RI,22400
+lattifai/caption/__init__.py,sha256=6MM_2j6CaqwZ81LfSy4di2EP0ykvheRjMZKAYDx2rQs,477
+lattifai/caption/caption.py,sha256=mZYobxuZ8tkJUkZMVvRTrNeGTdmIZYSXTEySQdaGQd8,54595
+lattifai/caption/gemini_reader.py,sha256=GqY2w78xGYCMDP5kD5WGS8jK0gntel2SK-EPpPKTrwU,15138
+lattifai/caption/gemini_writer.py,sha256=sYPxYEmVQcEan5WVGgSrcraxs3QJRQRh8CJkl2yUQ1s,6515
+lattifai/caption/supervision.py,sha256=DRrM8lfKU_x9aVBcLG6xnT0xIJrnc8jzHpzcSwQOg8c,905
+lattifai/caption/text_parser.py,sha256=XDb8KTt031uJ1hg6dpbINglGOTX-6pBcghbg3DULM1I,4633
+lattifai/cli/__init__.py,sha256=LafsAf8YfDcfTeJ1IevFcyLm-mNbxpOOnm33OFKtpDM,523
+lattifai/cli/alignment.py,sha256=06em-Uaf6NhSz1ce4dwT2r8n56NrtibR7ZsSkmc18Kc,5954
+lattifai/cli/app_installer.py,sha256=gAndH3Yo97fGRDe2CQnGtOgZZ4k3_v5ftcUo5g6xbSA,5884
+lattifai/cli/caption.py,sha256=4qQ9DFhxcfaeFMY0TB5I42x4W_gOo2zY6kjXnHnFDms,6313
+lattifai/cli/diarization.py,sha256=cDz1p6RUC-ySPzzGYHWff0L6EWHTUPrci7DaVxwZrVc,3933
+lattifai/cli/server.py,sha256=sXMfOSse9-V79slXUU8FDLeqtI5U9zeU-5YpjTIGyVw,1186
+lattifai/cli/transcribe.py,sha256=_vHzrdaGiPepQWATqvEDYDjwzfVLAd2i8RjOLkvdb0w,8218
+lattifai/cli/youtube.py,sha256=-EIDSS1Iel3_6qD9M2CZZHwKOvgdkIa1cMY4rX7xwVo,5331
+lattifai/config/__init__.py,sha256=Z8OudvS6fgfLNLu_2fvoXartQiYCECOnNfzDt-PfCN4,543
+lattifai/config/alignment.py,sha256=vLiH150YWvBUiVkFOIO-nPXCB-b8fP9iSZgS79k1Qbg,4586
+lattifai/config/caption.py,sha256=AYOyUJ1xZsX8CBZy3GpLitbcCAHcZ9LwXui_v3vtuso,6786
+lattifai/config/client.py,sha256=I1JqLQlsQNU5ouovTumr-PP_8GWC9DI_e9B5UwsDZws,1492
+lattifai/config/diarization.py,sha256=cIkwCfsYqfMns3i6tKWcwBBBkdnhhmB_Eo0TuOPCw9o,2484
+lattifai/config/media.py,sha256=cjM8eGeZ7ELhmy4cCqHAyogeHItaVqMrPzSwwIx79HY,14856
+lattifai/config/transcription.py,sha256=_gPJD6cob_jWNdf841nBHhAqJGCxS6PfSyvx2W_vPcM,3082
+lattifai/diarization/__init__.py,sha256=MgBDQ1ehL2qDnZprEp8KqON7CmbG-qaP37gzBsV0jzk,119
+lattifai/diarization/lattifai.py,sha256=tCnFL6ywITqeKR8YoCsYvyJxNoIwoC6GsnI9zkXNB-Q,3128
+lattifai/server/app.py,sha256=wXYgXc_yGQACtUJdhkfhLsTOQjhhIhDQRiVRny7Ogcs,15455
+lattifai/transcription/__init__.py,sha256=vMHciyCEPKhhfM3KjMCeDqnyxU1oghF8g5o5SvpnT_4,2669
+lattifai/transcription/base.py,sha256=v_b1_JGYiBqeMmwns0wHCJ7UOm6j9k-76Uzbr-qmzrs,4467
+lattifai/transcription/gemini.py,sha256=LJSQt9nGqQdEG6ZFXoHWltumyMEM7-Ezy8ss0iPJb7k,12414
+lattifai/transcription/lattifai.py,sha256=EKEdCafgdRWKw_084eD07BqGh2_D-qo3ig3H5X3XYGg,4621
+lattifai/transcription/prompts/README.md,sha256=X49KWSQVdjWxxWUp4R2w3ZqKrAOi6_kDNHh1hMaQ4PE,694
+lattifai/transcription/prompts/__init__.py,sha256=G9b42COaCYv3sPPNkHsGDLOMBuVGKt4mXGYal_BYtYQ,1351
+lattifai/transcription/prompts/gemini/README.md,sha256=rt7f7yDGtaobKBo95LG3u56mqa3ABOXQd0UVgJYtYuo,781
+lattifai/transcription/prompts/gemini/transcription_gem.txt,sha256=cljzZ--BDgnnKzqVCakr-fTp2Xk38UOsUquvruNX-LU,4600
+lattifai/workflow/__init__.py,sha256=GOT9jptXwpIMiNRqJ_LToEt_5Dt0k7XXbLkFzhrl31o,548
+lattifai/workflow/agents.py,sha256=yEOnxnhcTvr1iOhCorNvp8B76P6nQsLRXJCu_rCYFfM,38
+lattifai/workflow/base.py,sha256=8QoVIBZwJfr5mppJbtUFafHv5QR9lL-XrULjTWD0oBg,6257
+lattifai/workflow/file_manager.py,sha256=IUWW838ta83kfwM4gpW83gsD_Tx-pa-L_RWKjiefQbQ,33017
+lattifai/workflow/youtube.py,sha256=ON9z0UUk16ThQzdhdgyOiwBmewZOcxfT05dsl3aKYqw,23840
+lattifai-1.1.0.dist-info/licenses/LICENSE,sha256=xGMLmdFJy6Jkz3Hd0znyQLmcxC93FSZB5isKnEDMoQQ,1066
+lattifai-1.1.0.dist-info/METADATA,sha256=MXg4IXWA38Y9c_RT9S_6NnCZFc_4-Yic_zZDHlS1TeY,26400
+lattifai-1.1.0.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+lattifai-1.1.0.dist-info/entry_points.txt,sha256=nHZri2VQkPYEl0tQ0dMYTpVGlCOgVWlDG_JtDR3QXF8,545
+lattifai-1.1.0.dist-info/top_level.txt,sha256=tHSoXF26r-IGfbIP_JoYATqbmf14h5NrnNJGH4j5reI,9
+lattifai-1.1.0.dist-info/RECORD,,

{lattifai-1.0.4.dist-info → lattifai-1.1.0.dist-info}/entry_points.txt

@@ -1,6 +1,7 @@
 [console_scripts]
 lai-align = lattifai.cli.alignment:main
 lai-app-install = lattifai.cli.app_installer:main
+lai-diarize = lattifai.cli.diarization:main
 lai-server = lattifai.cli.server:main
 lai-transcribe = lattifai.cli.transcribe:main
 lai-youtube = lattifai.cli.youtube:main
@@ -11,4 +12,5 @@ laicap-shift = lattifai.cli.caption:main_shift
 [lai_run.cli]
 alignment = lattifai.cli
 caption = lattifai.cli
+diarization = lattifai.cli
 transcribe = lattifai.cli

{lattifai-1.0.4.dist-info → lattifai-1.1.0.dist-info}/licenses/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 Lattifai.
+Copyright (c) 2025 LattifAI.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

lattifai-1.0.4.dist-info/RECORD

@@ -1,56 +0,0 @@
-lattifai/__init__.py,sha256=K46XVINrXgjGehO8uXByTIbUnBCdB7QwsvVNWzKbdeU,2364
-lattifai/audio2.py,sha256=WPAhcaEoIMRQBf2QZe-0yyAbgyyiqUVAthJ-z54R9Wc,7761
-lattifai/client.py,sha256=Wkz7Q1XvCQ9KxD0uZ_M1ix457ZbgIG1gAxxt8nMBUj4,22147
-lattifai/errors.py,sha256=dFQ_7c8rwuHrq2pDPjpzA755tAV3t8daXXFbHmWblbs,11015
-lattifai/logging.py,sha256=MbUEeOUFlF92pA9v532DiPPWKl03S7UHCJ6Z652cf0w,2860
-lattifai/mixin.py,sha256=2QnWMG2E_cyZaa98Wtdf6Duo8w3DTIiD-EEfrmtDhGk,23388
-lattifai/types.py,sha256=SjYBfwrCBOXlICvH04niFQJ7OzTx7oTaa_npfRkB67U,659
-lattifai/utils.py,sha256=TqOPrd_Et7KxrbfI_JbBNIGZ5-oGJY8ZUyJMPDTih1I,3848
-lattifai/alignment/__init__.py,sha256=ehpkKfjNIYUx7_M-RWD_8Efcrzd9bE-NSm0QgMMVLW0,178
-lattifai/alignment/lattice1_aligner.py,sha256=soBRZ98jRIju-wN5eqYUmQfF56KiEUxVGw0UvtRcx4A,4464
-lattifai/alignment/lattice1_worker.py,sha256=XGICEzLygspqC7SMj5s45M7VNSj-l2zemkawdKKjssw,9233
-lattifai/alignment/phonemizer.py,sha256=fbhN2DOl39lW4nQWKzyUUTMUabg7v61lB1kj8SKK-Sw,1761
-lattifai/alignment/segmenter.py,sha256=-FKtIwv9Z4fU9Fs08jhL9VyREVSYcfcwuTqb8jxCiuo,6228
-lattifai/alignment/tokenizer.py,sha256=WilqU9Ecdkl_cW86IkB1mh_PFlHN-35Jsreiyse2r-8,22355
-lattifai/caption/__init__.py,sha256=6MM_2j6CaqwZ81LfSy4di2EP0ykvheRjMZKAYDx2rQs,477
-lattifai/caption/caption.py,sha256=NNkBJbSdfXe4CwlCvMplrd4UOxlZyxq5Cs5g-dReB1E,46974
-lattifai/caption/gemini_reader.py,sha256=GqY2w78xGYCMDP5kD5WGS8jK0gntel2SK-EPpPKTrwU,15138
-lattifai/caption/gemini_writer.py,sha256=sYPxYEmVQcEan5WVGgSrcraxs3QJRQRh8CJkl2yUQ1s,6515
-lattifai/caption/supervision.py,sha256=DRrM8lfKU_x9aVBcLG6xnT0xIJrnc8jzHpzcSwQOg8c,905
-lattifai/caption/text_parser.py,sha256=XDb8KTt031uJ1hg6dpbINglGOTX-6pBcghbg3DULM1I,4633
-lattifai/cli/__init__.py,sha256=dIUmrpN-OwR4h6BqMhXp87_5ZwgO41ShPru_iZGnpQs,463
-lattifai/cli/alignment.py,sha256=uKMTE95_JMikfbyCcwLbQxms-EQmZXEj7oYugiupk9I,5890
-lattifai/cli/app_installer.py,sha256=0xBQnJZKhyx4JT_PkHXkZ0XlAWxCGz9o0Jjq99poKew,5680
-lattifai/cli/caption.py,sha256=ucgYxJ43ab71nGpZBAiVn8QA0DAVht2QMZFE5IdgxP0,6853
-lattifai/cli/server.py,sha256=Vo6_ANgwu7WtC5h4BebQLmhqLNpqzPoYrPQPANpP7rw,1142
-lattifai/cli/transcribe.py,sha256=6uJfvtB1o_u1uQwxt4fje_koyfN93mGaFLlskmjqx2c,7406
-lattifai/cli/youtube.py,sha256=9_erdIkhX8pCiy7BRzNstEiO9saM-VKZ1WVqvbXbmrc,5267
-lattifai/config/__init__.py,sha256=Z8OudvS6fgfLNLu_2fvoXartQiYCECOnNfzDt-PfCN4,543
-lattifai/config/alignment.py,sha256=z0b9tg67ftDI90j9Td3qmXFg3WZjSbgszjzeTdwrjZA,3291
-lattifai/config/caption.py,sha256=nmfdsJ-18l4UmapdVgxF1ARJbA4aOr7jek1bmse2F_E,6787
-lattifai/config/client.py,sha256=I1JqLQlsQNU5ouovTumr-PP_8GWC9DI_e9B5UwsDZws,1492
-lattifai/config/diarization.py,sha256=cIkwCfsYqfMns3i6tKWcwBBBkdnhhmB_Eo0TuOPCw9o,2484
-lattifai/config/media.py,sha256=5JOPjifXDM2WWQERySDZen4-7YfgQNcYM2NkkKp0LjQ,13610
-lattifai/config/transcription.py,sha256=bzghOGgcNWzTnDYd_cqCOB7GT8OnzHDiyam7LSixqxM,2901
-lattifai/diarization/__init__.py,sha256=MgBDQ1ehL2qDnZprEp8KqON7CmbG-qaP37gzBsV0jzk,119
-lattifai/diarization/lattifai.py,sha256=SE2BpIZ3_deKyhXdBqe77bsDLXIUV9AQV34gfINv7_s,2657
-lattifai/server/app.py,sha256=UpHsKJHtK1-sdp5mtDPBSxEl8xYTbe7cVO8dLp9Xiuo,15380
-lattifai/transcription/__init__.py,sha256=mEoMTbs5jAgtXQn1jTjlFY_GUr-S0WmPn8uZ6WZCkU0,2643
-lattifai/transcription/base.py,sha256=59b4nQHFMyTRyyzBJTM8ZpEuUy1KjwA2o6rNfrNluKY,3911
-lattifai/transcription/gemini.py,sha256=1VNi9gl-Kpkw3ljZcOZG5oq_OY8fMC9Xv4kOwyQpI0Q,7992
-lattifai/transcription/lattifai.py,sha256=h0nhXST0qljhyndf80IEddM7Y_N1jiS28YoaE536eME,3483
-lattifai/transcription/prompts/README.md,sha256=X49KWSQVdjWxxWUp4R2w3ZqKrAOi6_kDNHh1hMaQ4PE,694
-lattifai/transcription/prompts/__init__.py,sha256=G9b42COaCYv3sPPNkHsGDLOMBuVGKt4mXGYal_BYtYQ,1351
-lattifai/transcription/prompts/gemini/README.md,sha256=rt7f7yDGtaobKBo95LG3u56mqa3ABOXQd0UVgJYtYuo,781
-lattifai/transcription/prompts/gemini/transcription_gem.txt,sha256=cljzZ--BDgnnKzqVCakr-fTp2Xk38UOsUquvruNX-LU,4600
-lattifai/workflow/__init__.py,sha256=GOT9jptXwpIMiNRqJ_LToEt_5Dt0k7XXbLkFzhrl31o,548
-lattifai/workflow/agents.py,sha256=yEOnxnhcTvr1iOhCorNvp8B76P6nQsLRXJCu_rCYFfM,38
-lattifai/workflow/base.py,sha256=8QoVIBZwJfr5mppJbtUFafHv5QR9lL-XrULjTWD0oBg,6257
-lattifai/workflow/file_manager.py,sha256=d106KHLY8A9amLy5h1vR32e4od8mmJGqMD-iDyiRPLI,32917
-lattifai/workflow/youtube.py,sha256=n8L1c6tl8FuYzAzKZ-B76zf5yZsvVggZEJ9mPdbEWGQ,22989
-lattifai-1.0.4.dist-info/licenses/LICENSE,sha256=_IkHdwOWLAWcE1M_tIpDoRWdNSJwFdtIqI-XSkK3yPU,1066
-lattifai-1.0.4.dist-info/METADATA,sha256=uijheuHzvh-AhZwIFCGTc2_UX-x3ZXxhnlPsvcaMQ4c,24582
-lattifai-1.0.4.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-lattifai-1.0.4.dist-info/entry_points.txt,sha256=F8Akof3VtKtrbnYSav1umgoo9Xbv34rUcKn-ioRfeGQ,474
-lattifai-1.0.4.dist-info/top_level.txt,sha256=tHSoXF26r-IGfbIP_JoYATqbmf14h5NrnNJGH4j5reI,9
-lattifai-1.0.4.dist-info/RECORD,,