mrq/vall-e
5
9
Fork 0
Code Issues 8 Pull Requests Packages Projects Releases Wiki Activity

fixes to process_emilia.py script

Browse Source
This commit is contained in:
mrq 2024-12-09 14:38:09 -06:00
parent a6c745bafb
commit fc5e6d8599
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
scripts/process_emilia.py
View File

@ -110,8 +110,6 @@ def process(
if only_speakers and speaker_group not in only_speakers: if only_speakers and speaker_group not in only_speakers:
continue continue
os.makedirs(f'./{output_dataset}/{group_name}/{speaker_group}/', exist_ok=True)
if f'{group_name}/{speaker_group}' not in dataset: if f'{group_name}/{speaker_group}' not in dataset:
dataset.append(f'{group_name}/{speaker_group}') dataset.append(f'{group_name}/{speaker_group}')
@ -130,13 +128,14 @@ def process(
extension = os.path.splitext(filename)[-1][1:] extension = os.path.splitext(filename)[-1][1:]
fname = filename.replace(f'.{extension}', "") fname = filename.replace(f'.{extension}', "")
if "text" not in metadata:
continue
waveform, sample_rate = None, None waveform, sample_rate = None, None
metadata = json.load(open(jsonpath, "r", encoding="utf-8")) metadata = json.load(open(jsonpath, "r", encoding="utf-8"))
if "text" not in metadata:
continue
speaker_id = metadata["speaker"] speaker_id = metadata["speaker"]
outpath = Path(f'./{output_dataset}/{group_name}/{speaker_id}/{fname}.{extension}') outpath = Path(f'./{output_dataset}/{group_name}/{speaker_group}/{speaker_id}/{fname}.{extension}')
os.makedirs(f'./{output_dataset}/{group_name}/{speaker_group}/{speaker_id}/', exist_ok=True)
if _replace_file_extension(outpath, audio_extension).exists(): if _replace_file_extension(outpath, audio_extension).exists():
continue continue