deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 09:29:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix cosyvoice3 training

Browse Source
This commit is contained in:
lyuxiang.lx
2025-12-29 10:02:59 +00:00
parent 8524c81acd
commit 4d7295a9a7
5 changed files with 25 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
cosyvoice/dataset/processor.py
View File

@@ -26,7 +26,7 @@ import pyworld as pw
AUDIO_FORMAT_SETS = {'flac', 'mp3', 'm4a', 'ogg', 'opus', 'wav', 'wma'}
def parquet_opener(data, mode='train', tts_data={}):
def parquet_opener(data, mode='train'):
""" Give url or local file, return file descriptor
Inplace operation.
@@ -44,12 +44,8 @@ def parquet_opener(data, mode='train', tts_data={}):
df = df.to_pandas()
for i in range(len(df)):
sample.update(dict(df.loc[i]))
if mode == 'train':
# NOTE do not return sample directly, must initialize a new dict
yield {**sample}
else:
for index, text in enumerate(tts_data[df.loc[i, 'utt']]):
yield {**sample, 'tts_index': index, 'tts_text': text}
# NOTE do not return sample directly, must initialize a new dict
yield {**sample}
except Exception as ex:
logging.warning('Failed to open {}, ex info {}'.format(url, ex))