MontrealCorpusTools / Montreal-Forced-Aligner

Command line utility for forced alignment using Kaldi
https://montrealcorpustools.github.io/Montreal-Forced-Aligner/
MIT License
1.31k stars 244 forks source link

no successful alignments #719

Open OreoluwaBabatunde opened 10 months ago

OreoluwaBabatunde commented 10 months ago

I am using a swahilli corpus that already has a pretrained acoustic model and dictionary from mfa. (mfa_env) C:\Users\user\Downloads\ALL>mfa align C:\Users\user\Downloads\ALL\dev C:\Users\user\Downloads\ALL\MFA\pretrained_models\dictionary\swahili_mfa.dict C:\Users\user\Downloads\ALL\MFA\swahili_mfa C:\Users\user\Downloads\ALL\Alignments.

I am using miniconda prompt on windows

this is the error below.

ERROR There was an error in the run, please see the log. Error in atexit._run_exitfuncs: Traceback (most recent call last): File "C:\Users\user\miniconda3\envs\mfa_env\Scripts\mfa-script.py", line 9, in sys.exit(mfa_cli()) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\click\core.py", line 1157, in call return self.main(args, kwargs) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\rich_click\rich_command.py", line 126, in main rv = self.invoke(ctx) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\click\core.py", line 1688, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\click\core.py", line 1434, in invoke return ctx.invoke(self.callback, ctx.params) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\click\core.py", line 783, in invoke return __callback(args, *kwargs) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\click\decorators.py", line 33, in new_func return f(get_current_context(), args, **kwargs) File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\montreal_forced_aligner\command_line\align.py", line 113, in align_corpus_cli aligner.align() File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\montreal_forced_aligner\alignment\pretrained.py", line 413, in align super().align() File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\montreal_forced_aligner\alignment\base.py", line 350, in align self.align_utterances() File "C:\Users\user\miniconda3\envs\mfa_env\lib\site-packages\montreal_forced_aligner\alignment\mixins.py", line 447, in align_utterances raise NoAlignmentsError( montreal_forced_aligner.exceptions.NoAlignmentsError: NoAlignmentsError:

There were no successful alignments for 211 utterances. The current set up used a beam of 10 and a retry beam of 40. You can try rerunning with a larger beam (i.e. "mfa align ... --beam 100 --retry_beam 400"). If increasing the beam size does not help, then there are likely issues with the corpus, dictionary, or acoustic model, and can be further diagnosed with the "mfa validate" command

rukix1ng commented 9 months ago

i also faced with this same issue

My-captain commented 9 months ago

same issue

maxime-fily commented 5 months ago

Same issue on Russian_mfa