deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #639 from FunAudioLLM/dev/lyuxiang.lx

Browse Source 
use stream read to save memory
This commit is contained in:
Xiang Lyu
2024-11-11 22:17:21 +08:00
committed by GitHub
parent 6d22d0b76f 5ed5bb15c8
commit 7701325969
1 changed files with 12 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
cosyvoice/dataset/processor.py
View File

@@ -40,7 +40,8 @@ def parquet_opener(data, mode='train', tts_data={}):
assert 'src' in sample assert 'src' in sample
url = sample['src'] url = sample['src']
try: try:
df = pq.read_table(url).to_pandas() for df in pq.ParquetFile(url).iter_batches(batch_size=64):
df = df.to_pandas()
for i in range(len(df)): for i in range(len(df)):
if mode == 'inference' and df.loc[i, 'utt'] not in tts_data: if mode == 'inference' and df.loc[i, 'utt'] not in tts_data:
continue continue