cjm-transcript-segment-align 0.0.1__py3-none-any.whl

cjm_transcript_segment_align/services/forced_alignment.py

@@ -0,0 +1,301 @@
+"""Forced alignment service for audio-informed text pre-splitting via forced alignment plugin"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/services/forced_alignment.ipynb.
+
+# %% auto #0
+__all__ = ['map_fa_words_to_text', 'assign_words_to_chunks', 'build_segments_from_alignment', 'ForcedAlignmentService']
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-imports
+import re
+import asyncio
+from typing import List, Dict, Any, Optional, Tuple
+
+from cjm_plugin_system.core.manager import PluginManager
+
+from cjm_transcription_plugin_system.forced_alignment_core import ForcedAlignItem, ForcedAlignResult
+from cjm_transcript_segmentation.models import TextSegment
+from cjm_transcript_vad_align.models import VADChunk
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-strip-punct
+# Regex to strip punctuation for comparison (matches what FA models strip)
+_PUNCT_RE = re.compile(r'[^\w\s]', re.UNICODE)
+
+
+def _strip_punct(text: str) -> str:
+    """Strip punctuation from text for comparison with FA output."""
+    return _PUNCT_RE.sub('', text)
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-map-words
+def map_fa_words_to_text(
+    text: str,  # Original text with punctuation
+    fa_items: List[ForcedAlignItem],  # FA word-level alignment results
+) -> List[Tuple[int, int]]:  # List of (start_char, end_char) spans into original text
+    """Map forced alignment words back to character spans in the original text.
+    
+    Walks through the original text, matching each FA word (punctuation-stripped)
+    against original text tokens. Returns character offset pairs for each FA word.
+    """
+    spans = []
+    pos = 0  # Current position in original text
+    
+    for item in fa_items:
+        fa_word = item.text.lower()
+        
+        # Skip whitespace to find next token start
+        while pos < len(text) and text[pos].isspace():
+            pos += 1
+        
+        if pos >= len(text):
+            break
+        
+        # Find the end of the current token in original text
+        # A token is a run of non-space characters
+        token_start = pos
+        token_end = pos
+        while token_end < len(text) and not text[token_end].isspace():
+            token_end += 1
+        
+        orig_token = text[token_start:token_end]
+        stripped_token = _strip_punct(orig_token).lower()
+        
+        # Check if FA word matches this token (after stripping punctuation)
+        if stripped_token == fa_word:
+            spans.append((token_start, token_end))
+            pos = token_end
+        else:
+            # Handle multi-token FA words (e.g., "p.m." → "pm") or
+            # cases where the original has punctuation splitting tokens
+            # Try consuming multiple tokens until the stripped concatenation matches
+            concat = stripped_token
+            scan_end = token_end
+            matched = False
+            
+            # Try up to 3 extra tokens for cases like "p.m." → "p" + "." + "m" + "."
+            for _ in range(3):
+                if concat.lower() == fa_word:
+                    spans.append((token_start, scan_end))
+                    pos = scan_end
+                    matched = True
+                    break
+                # Skip whitespace
+                while scan_end < len(text) and text[scan_end].isspace():
+                    scan_end += 1
+                if scan_end >= len(text):
+                    break
+                # Consume next token
+                next_start = scan_end
+                while scan_end < len(text) and not text[scan_end].isspace():
+                    scan_end += 1
+                concat += _strip_punct(text[next_start:scan_end])
+            
+            if not matched:
+                # Check final concatenation
+                if concat.lower() == fa_word:
+                    spans.append((token_start, scan_end))
+                    pos = scan_end
+                else:
+                    # Fallback: skip this original token and try again
+                    # (handles insertions/deletions between transcript and FA output)
+                    spans.append((token_start, token_end))
+                    pos = token_end
+    
+    return spans
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-assign-chunks
+def assign_words_to_chunks(
+    fa_items: List[ForcedAlignItem],  # FA word-level alignment results
+    vad_chunks: List[VADChunk],  # VAD chunks with start/end times
+) -> List[int]:  # Chunk index for each FA word
+    """Assign each FA word to a VAD chunk based on timestamp overlap.
+    
+    Words whose start_time falls within a chunk's [start, end] range are
+    assigned to that chunk. Words in silence gaps are assigned to the
+    nearest chunk by time proximity.
+    """
+    if not vad_chunks:
+        return [0] * len(fa_items)
+    
+    assignments = []
+    
+    for item in fa_items:
+        t = item.start_time
+        best_idx = 0
+        best_dist = float('inf')
+        contained = False
+        
+        for i, chunk in enumerate(vad_chunks):
+            # Strict containment (no tolerance)
+            if chunk.start_time <= t <= chunk.end_time:
+                best_idx = i
+                contained = True
+                break
+            
+            # Track nearest chunk for gap assignment
+            dist = min(abs(t - chunk.start_time), abs(t - chunk.end_time))
+            if dist < best_dist:
+                best_dist = dist
+                best_idx = i
+        
+        assignments.append(best_idx)
+    
+    return assignments
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-build-segments
+def build_segments_from_alignment(
+    text: str,  # Original text with punctuation
+    spans: List[Tuple[int, int]],  # Character spans from map_fa_words_to_text
+    assignments: List[int],  # Chunk index per word from assign_words_to_chunks
+    num_chunks: int,  # Total number of VAD chunks
+    source_id: Optional[str] = None,  # Source block ID for traceability
+    source_provider_id: Optional[str] = None,  # Source provider identifier
+) -> List[TextSegment]:  # One segment per VAD chunk
+    """Build TextSegment list by grouping words by their assigned VAD chunk.
+    
+    Each VAD chunk gets one TextSegment whose text is the joined original
+    (punctuated) words assigned to that chunk.
+    """
+    # Group spans by chunk assignment
+    chunk_spans: Dict[int, List[Tuple[int, int]]] = {}
+    for span, chunk_idx in zip(spans, assignments):
+        if chunk_idx not in chunk_spans:
+            chunk_spans[chunk_idx] = []
+        chunk_spans[chunk_idx].append(span)
+    
+    segments = []
+    for chunk_idx in range(num_chunks):
+        word_spans = chunk_spans.get(chunk_idx, [])
+        
+        if word_spans:
+            # Extract text from original using spans
+            # Use the full range from first word start to last word end
+            seg_start = word_spans[0][0]
+            seg_end = word_spans[-1][1]
+            seg_text = text[seg_start:seg_end].strip()
+        else:
+            # Empty segment (VAD chunk with no assigned words)
+            seg_text = ""
+            seg_start = None
+            seg_end = None
+        
+        segments.append(TextSegment(
+            index=chunk_idx,
+            text=seg_text,
+            source_id=source_id,
+            source_provider_id=source_provider_id,
+            start_char=seg_start,
+            end_char=seg_end,
+        ))
+    
+    return segments
+
+# %% ../../nbs/services/forced_alignment.ipynb #cell-service
+class ForcedAlignmentService:
+    """Service for audio-informed text pre-splitting via forced alignment plugin."""
+
+    def __init__(
+        self,
+        plugin_manager: PluginManager,  # Plugin manager for accessing forced alignment plugin
+        plugin_name: str = "cjm-transcription-plugin-qwen3-forced-aligner",  # Name of the FA plugin
+    ):
+        """Initialize the forced alignment service."""
+        self._manager = plugin_manager
+        self._plugin_name = plugin_name
+
+    def is_available(self) -> bool:  # True if plugin is loaded and ready
+        """Check if the forced alignment plugin is available."""
+        return self._manager.get_plugin(self._plugin_name) is not None
+
+    def ensure_loaded(
+        self,
+        config: Optional[Dict[str, Any]] = None,  # Optional plugin configuration
+    ) -> bool:  # True if successfully loaded
+        """Ensure the forced alignment plugin is loaded."""
+        if self.is_available():
+            return True
+        meta = self._manager.get_discovered_meta(self._plugin_name)
+        if meta:
+            return self._manager.load_plugin(meta, config or {"language": "English"})
+        return False
+
+    async def align_and_split_async(
+        self,
+        audio_path: str,  # Path to the audio file
+        text: str,  # Original transcript text blob (with punctuation)
+        vad_chunks: List[VADChunk],  # VAD chunks for this audio
+        source_id: Optional[str] = None,  # Source block ID for traceability
+        source_provider_id: Optional[str] = None,  # Source provider identifier
+    ) -> List[TextSegment]:  # One segment per VAD chunk
+        """Run forced alignment and split text into segments matching VAD chunks."""
+        if not self.is_available():
+            raise RuntimeError(f"Plugin {self._plugin_name} not loaded")
+
+        # 1. Call forced alignment plugin
+        result = await self._manager.execute_plugin_async(
+            self._plugin_name,
+            audio=audio_path,
+            text=text,
+        )
+
+        # Convert dict result to ForcedAlignItem objects
+        items = [
+            ForcedAlignItem(**item_dict)
+            for item_dict in result.get("items", [])
+        ]
+
+        # 2. Map FA words back to original text positions
+        spans = map_fa_words_to_text(text, items)
+
+        # 3. Assign words to VAD chunks
+        assignments = assign_words_to_chunks(items, vad_chunks)
+
+        # 4-5. Group by chunk and build TextSegments
+        segments = build_segments_from_alignment(
+            text=text,
+            spans=spans,
+            assignments=assignments,
+            num_chunks=len(vad_chunks),
+            source_id=source_id,
+            source_provider_id=source_provider_id,
+        )
+
+        return segments
+
+    def align_and_split(
+        self,
+        audio_path: str,  # Path to the audio file
+        text: str,  # Original transcript text blob
+        vad_chunks: List[VADChunk],  # VAD chunks for this audio
+        source_id: Optional[str] = None,
+        source_provider_id: Optional[str] = None,
+    ) -> List[TextSegment]:  # One segment per VAD chunk
+        """Run forced alignment and split text synchronously."""
+        return asyncio.get_event_loop().run_until_complete(
+            self.align_and_split_async(
+                audio_path, text, vad_chunks, source_id, source_provider_id
+            )
+        )
+
+    async def align_and_split_combined_async(
+        self,
+        source_blocks: List[Any],  # SourceBlock objects with id, provider_id, text
+        audio_paths: List[str],  # Audio file path per source block
+        vad_chunks_by_source: List[List[VADChunk]],  # VAD chunks per source block
+    ) -> List[TextSegment]:  # Combined segments with global indexing
+        """Align and split multiple source blocks with their respective audio."""
+        all_segments = []
+        global_index = 0
+
+        for block, audio_path, chunks in zip(source_blocks, audio_paths, vad_chunks_by_source):
+            segments = await self.align_and_split_async(
+                audio_path=audio_path,
+                text=block.text,
+                vad_chunks=chunks,
+                source_id=block.id,
+                source_provider_id=block.provider_id,
+            )
+            for seg in segments:
+                seg.index = global_index
+                global_index += 1
+                all_segments.append(seg)
+
+        return all_segments

cjm_transcript_segment_align-0.0.1.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.