def combine_wavs_batch(audio_paths, method, **kargv):
audio_paths.sort()
method = method.lower()
if method == "librosa":
fn = partial(split_on_silence_with_librosa, **kargv)
elif method == "pydub":
fn = partial(split_on_silence_with_pydub, **kargv)
parallel_run(fn, audio_paths,
desc="Split on silence", parallel=False)
audio_path = audio_paths[0]
spl = os.path.basename(audio_path).split('.', 1)
prefix = os.path.dirname(audio_path)+"/"+spl[0]+"."
in_ext = audio_path.rsplit(".")[1]
data = load_json(config.alignment_path, encoding="utf8")
#print(data)
for i in range(len(wavs)-1):
if len(wavs[i]) > 15000:
continue
if not paths[i] in data:
continue
sum = len(wavs[i])
filename = prefix + str(i).zfill(4)+"."
asr = data[paths[i]]+" "
concated = wavs[i]
for j in range(i+1, len(wavs)):
sum += len(wavs[j])
sum += 400
if sum > 15000:
break
if not paths[j] in data:
break
filename = filename + str(j).zfill(4) + "."
asr = asr + data[paths[j]] + " "
concated = concated + silence + wavs[j]
final_fn = filename+"wav"
data[final_fn] = asr
concated.export(final_fn, format="wav")
print(filename+"wav | "+str(len(concated)))
if os.path.exists(config.alignment_path):
backup_file(config.alignment_path)
write_json(config.alignment_path, data)
get_durations(data.keys(), print_detail=False)
return 0
results.update(item)
found_count = sum([type(value) == str for value in results.values()])
print(" [*] # found: {:.5f}% ({}/{})".format(
len(results) / len(data), len(results), len(data)))
print(" [*] # exact match: {:.5f}% ({}/{})".format(
found_count / len(items), found_count, len(items)))
return results
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--recognition_path', required=True)
parser.add_argument('--alignment_filename', default="alignment.json")
parser.add_argument('--score_threshold', default=0.4, type=float)
parser.add_argument('--recognition_encoding', default='utf-8')
config, unparsed = parser.parse_known_args()
results = align_text_batch(config)
base_dir = os.path.dirname(config.recognition_path)
alignment_path = \
os.path.join(base_dir, config.alignment_filename)
if os.path.exists(alignment_path):
backup_file(alignment_path)
write_json(alignment_path, results)
duration = get_durations(results.keys(), print_detail=False)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--audio_pattern', required=True)
parser.add_argument('--alignment_path', required=True)
parser.add_argument('--out_ext', default='wav')
parser.add_argument('--method',
choices=['librosa', 'pydub'],
required=True)
config = parser.parse_args()
data = load_json(config.alignment_path, encoding="utf8")
audio_paths = glob(config.audio_pattern)
for path in audio_paths:
single_path = path.replace('.wav', '_s??.wav')
single_paths = glob(single_path)
combine_wavs_batch(
single_paths,
config.method,
out_ext=config.out_ext,
)
wavs = []
paths = []
if os.path.exists(config.alignment_path):
backup_file(config.alignment_path)
write_json(config.alignment_path, data)
get_durations(data.keys(), print_detail=False)
