def run_repetition(self, stepidx): """ Execute the automatic repetitions detection. """ # Initializations step = self.parameters.get_step(stepidx) stepname = self.parameters.get_step_name(stepidx) files_processed_success = 0 self._progress.set_header(stepname) self._progress.update(0,"") # Get the list of input file names, with the ".wav" (or ".wave") extension filelist = self.set_filelist(".wav",not_start=["track_"]) if len(filelist) == 0: return 0 total = len(filelist) # Create annotation instance try: self._progress.set_text("Loading resources...") r = sppasRepet( step.get_langresource(), self._logfile ) except Exception as e: if self._logfile is not None: self._logfile.print_message( "%s\n"%str(e), indent=1,status=4 ) return 0 for i,f in enumerate(filelist): # fix the default values r.fix_options( step.get_options() ) # Indicate the file to be processed self._progress.set_text( os.path.basename(f)+" ("+str(i+1)+"/"+str(total)+")" ) if self._logfile is not None: self._logfile.print_message(stepname+" of file " + f, indent=1 ) # Get the input file ext = ['-palign'+self.parameters.get_output_format()] for e in annotationdata.io.extensions_out_multitiers: ext.append( '-palign'+e ) inname = self._get_filename(f, ext) if inname is not None: # Fix output file name outname = os.path.splitext(f)[0] + '-ralign' + self.parameters.get_output_format() # Execute annotation try: r.run( inname, None, outname ) except Exception as e: if self._logfile is not None: self._logfile.print_message( "%s for file %s\n"%(str(e),outname), indent=2,status=-1 ) else: files_processed_success += 1 if self._logfile is not None: self._logfile.print_message(outname, indent=2,status=0 ) else: if self._logfile is not None: self._logfile.print_message("Failed to find a file with time-aligned tokens. Read the documentation for details.",indent=2,status=2) # Indicate progress self._progress.set_fraction(float((i+1))/float(total)) if self._logfile is not None: self._logfile.print_newline() # Indicate completed! self._progress.update(1,"Completed (%d files successfully over %d files).\n"%(files_processed_success,total)) self._progress.set_header("") return files_processed_success
SPPAS = os.path.join(os.path.dirname( os.path.dirname( PROGRAM ) ), "src") sys.path.append(SPPAS) from annotations.Repet.sppasrepet import sppasRepet # ---------------------------------------------------------------------------- # Verify and extract args: # ---------------------------------------------------------------------------- parser = ArgumentParser(usage="%s -i file [options]" % os.path.basename(PROGRAM), description="Self- and Other- repetitions detection.") parser.add_argument("-i", metavar="file", required=True, help='Input file name with time-aligned tokens of the main speaker') parser.add_argument("-r", metavar="file", help='Either the lemma dictionary or the list of stop-words') parser.add_argument("-I", metavar="file", help='Input file name with time-aligned tokens of the echoing-speaker (if ORs)') parser.add_argument("-o", metavar="file", help='Output file name') if len(sys.argv) <= 1: sys.argv.append('-h') args = parser.parse_args() # ---------------------------------------------------------------------------- # Automatic detection is here: # ---------------------------------------------------------------------------- p = sppasRepet( args.r ) p.run( args.i, args.I, args.o ) # ----------------------------------------------------------------------------