NeMo
English
audio
speech
forced-alignment
reference-text-alignment
speech-processing
mfa
whisperx
python
metric:mae
Eval Results (legacy)
Instructions to use vertox-ai/speech-text-data-aligners with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use vertox-ai/speech-text-data-aligners with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
Commit History
-
feat(whisperx): add reference-text alignment backend
- Add isolated WhisperX reference-text alignment with typed configuration and provider boundaries - Align authoritative transcripts directly without using Whisper ASR transcription as ground truth - Parse native word timings strictly with explicit missing-timestamp and alignment failure handling - Pin the WhisperX runtime and English WAV2VEC2 alignment model with reproducible provenance - Preserve heavyweight model imports inside the isolated worker and keep neutral imports optional - Preserve programming and systemic worker failures at the whole-process boundary - Add deterministic unit, architecture, coverage, and opt-in real integration tests - Record the real five-row evaluation with 5/5 successes and 0.0154 s first-word-end MAEc3b6e69 -
feat(mfa): add forced alignment backend
- Add typed MFA configuration, corpus materialization, subprocess execution, and TextGrid parsing - Preserve authoritative transcripts with reversible MFA-specific normalization and lexical mapping - Add strict handling for OOVs, silence intervals, malformed output, and timestamp validation - Keep MFA isolated in its dedicated Conda environment and behind the shared backend protocol - Add deterministic unit, architecture, coverage, and opt-in real integration tests - Record the real five-row MFA evaluation with 5/5 successes and 0.0162 s first-word-end MAE - Document runtime, model, dictionary, G2P, provenance, and Stage 4 readinessfab9ab0 -
feat(nemo): add forced alignment backend
- Add typed NeMo configuration, reference-text manifest generation, and isolated NFA execution - Parse native word CTMs into backend-neutral alignments with strict transcript reconciliation - Enforce authoritative reference-text mode and pinned NeMo script/runtime provenance - Preserve optional native alignment artifacts and expose them through benchmark reports - Add lazy library and CLI composition without importing NeMo or Torch in the parent process - Add deterministic unit, architecture, coverage, and opt-in real integration tests - Document reproducible NeMo setup and explicitly record the blocked five-row empirical run61fc10e
-
docs(aligners): freeze Stage 0 architecture and tooling
- Freeze the modular backend-neutral architecture for NeMo, MFA, and WhisperX - Record backend research, model/runtime decisions, and isolated environment specifications - Add repository agent instructions and alignment engineering contracts - Define reusable core, application, backend adapter, and CLI dependency boundaries - Enforce complete docstrings, type hints, focused tests, and 90% per-file coverage - Pin the Stage 1 quality toolchain and canonical lint, type, coverage, and import checks - Record immutable dataset inputs, validation hashes, and Stage 1 readiness02a36e8