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

move use_spk_embedding to processor

Browse Source
This commit is contained in:
lyuxiang.lx
2024-07-11 13:15:34 +08:00
parent 0fd15bb12b
commit 6cebcb3410
4 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
cosyvoice/dataset/processor.py
View File

@@ -308,7 +308,7 @@ def batch(data, batch_type='static', batch_size=16, max_frames_in_batch=12000, m
logging.fatal('Unsupported batch type {}'.format(batch_type))
def padding(data, mode='train'):
def padding(data, use_spk_embedding, mode='train'):
""" Padding the data into training data
Args:
@@ -362,4 +362,8 @@ def padding(data, mode='train'):
'tts_index': tts_index,
'tts_text_token': tts_text_token,
'tts_text_token_len': tts_text_token_len})
if use_spk_embedding is True:
batch["embedding"] = batch["spk_embedding"]
else:
batch["embedding"] = batch["utt_embedding"]
yield batch