5 Commits

Author SHA1 Message Date
Karel Vesely
0fdba34a70 Finalizing the code:
- adding some coderabbit suggestions.
- removing `word_table`, `decoding_graph` from aligner API (unused)
- improved consistency of variable names (confidences)
- updated docstrings
2025-09-15 16:27:23 +02:00
Karel Vesely
d5ff66c56d ctc_align.py, avoid shadowing a variable 2025-09-12 17:11:41 +02:00
Karel Vesely
ec6a8462e4 update of argparse help strings 2025-09-12 17:05:05 +02:00
Karel Vesely
ce7ec4f3cb integrating remarks from PR 2025-09-11 15:49:31 +02:00
Karel Vesely
77357ebb06 zipformer/ctc_align.py
- tool for forced-alignment with CTC model
- provides timeline, computes per-token and per-utterance acoustic confidences
- based on torchaudio `forced_align()`
- confidences are computed in several ways

other modifications:
- LibriSpeechAsrDataModel extended with `::load_manifest()` to allow
  passing-in cutset from CLI.
- update @custom_fwd @custom_bwd in scaling.py
- streaming_decode.py update errs/recogs/log filenames '-' <-> '_'
2025-09-08 17:31:49 +02:00