Handling 'No default align-model' errors #434
Description
When transcribing certain input files, whisper crashes when some languages are detected (see error below). From my testing, this happens with Welsh (cy) and Bulgarian (bg), but it probably happens with even more languages. Especially with multilingual input files, where it's necessary to use the auto-detect language setting, this is relatively bothersome, because there is no easy fix (as languages tend to be erroneously detected in these files anyway). Shouldn't there be a way to default to a certain, general align-model, or to skip alignment entirely?
`2026-03-18 13:53:01 - whisperx.alignment - ERROR - No default alignment model for language: cy. Please find a wav2vec2.0 model finetuned on this language at https://huggingface.co/models, then pass the model name via --align_model [MODEL_NAME]
Traceback (most recent call last):
File "/home/appuser/.local/share/uv/python/cpython-3.10.19-linux-x86_64-gnu/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/home/appuser/.local/share/uv/python/cpython-3.10.19-linux-x86_64-gnu/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/app/whisperx-env/WhisperX/whisperx/main.py", line 102, in
cli()
File "/app/whisperx-env/WhisperX/whisperx/main.py", line 98, in cli
transcribe_task(args, parser)
File "/app/whisperx-env/WhisperX/whisperx/transcribe.py", line 186, in transcribe_task
align_model, align_metadata = load_align_model(
File "/app/whisperx-env/WhisperX/whisperx/alignment.py", line 90, in load_align_model
raise ValueError(f"No default align-model for language: {language_code}")
ValueError: No default align-model for language: cy`