Merge pull request #3054 from lissyx/import-time

Report imported vs total audio time

bin/import_cv.py

@@ -93,6 +93,7 @@ def one_sample(sample):
     else:
         # This one is good - keep it for the target CSV
         rows.append((wav_filename, file_size, label))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
     return (counter, rows)

bin/import_cv2.py

@@ -78,6 +78,7 @@ def one_sample(args):
     else:
         # This one is good - keep it for the target CSV
         rows.append((os.path.split(wav_filename)[-1], file_size, label, sample[2]))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
 

bin/import_lingua_libre.py

@@ -91,6 +91,7 @@ def one_sample(sample):
     else:
         # This one is good - keep it for the target CSV
         rows.append((wav_filename, file_size, label))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
 

bin/import_m-ailabs.py

@@ -91,6 +91,7 @@ def one_sample(sample):
     else:
         # This one is good - keep it for the target CSV
         rows.append((wav_filename, file_size, label))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
     return (counter, rows)

bin/import_slr57.py

@@ -86,6 +86,7 @@ def one_sample(sample):
     else:
         # This one is good - keep it for the target CSV
         rows.append((wav_filename, file_size, label))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
 

bin/import_ts.py

@@ -93,6 +93,7 @@ def one_sample(sample):
     else:
         # This one is good - keep it for the target CSV
         rows.append((wav_filename, file_size, label))
+        counter["imported_time"] += frames
     counter["all"] += 1
     counter["total_time"] += frames
 

training/deepspeech_training/util/importers.py

@@ -8,7 +8,7 @@ from .helpers import secs_to_hours
 from collections import Counter
 
 def get_counter():
-    return Counter({'all': 0, 'failed': 0, 'invalid_label': 0, 'too_short': 0, 'too_long': 0, 'total_time': 0})
+    return Counter({'all': 0, 'failed': 0, 'invalid_label': 0, 'too_short': 0, 'too_long': 0, 'imported_time': 0, 'total_time': 0})
 
 def get_imported_samples(counter):
     return counter['all'] - counter['failed'] - counter['too_short'] - counter['too_long'] - counter['invalid_label']
@@ -23,7 +23,7 @@ def print_import_report(counter, sample_rate, max_secs):
         print('Skipped %d samples that were too short to match the transcript.' % counter['too_short'])
     if counter['too_long'] > 0:
         print('Skipped %d samples that were longer than %d seconds.' % (counter['too_long'], max_secs))
-    print('Final amount of imported audio: %s.' % secs_to_hours(counter['total_time'] / sample_rate))
+    print('Final amount of imported audio: %s from %s.' % (secs_to_hours(counter['imported_time'] / sample_rate), secs_to_hours(counter['total_time'] / sample_rate)))
 
 def get_importers_parser(description):
     parser = argparse.ArgumentParser(description=description)