fix cv3 train

This commit is contained in:
lyuxiang.lx
2025-12-26 10:16:58 +00:00
parent a14e063ead
commit 8524c81acd
2 changed files with 6 additions and 8 deletions

View File

@@ -40,11 +40,10 @@ def main():
with open('{}/spk2utt'.format(args.des_dir), 'w') as f:
for k, v in spk2utt.items():
f.write('{} {}\n'.format(k, ' '.join(v)))
if args.instruct is True:
if args.instruct != '':
with open('{}/instruct'.format(args.des_dir), 'w') as f:
for k, v in utt2text.items():
# NOTE in CosyVoice3, we add instruct in sequence
f.write('{} You are a helpful assistant.<|endofprompt|>\n'.format(k, v))
f.write('{} {}\n'.format(k, args.instruct))
return
@@ -55,8 +54,6 @@ if __name__ == "__main__":
parser.add_argument('--des_dir',
type=str)
parser.add_argument('--instruct',
action='store_true',
default=False,
help='create instruct file or not')
type=str)
args = parser.parse_args()
main()

View File

@@ -7,7 +7,7 @@ stop_stage=3
data_url=www.openslr.org/resources/60
data_dir=/mnt/lyuxiang.lx/data/tts/openslr/libritts
pretrained_model_dir=../../../pretrained_models/CosyVoice3-0.5B
pretrained_model_dir=../../../pretrained_models/Fun-CosyVoice3-0.5B
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
echo "Data Download"
@@ -20,7 +20,8 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo "Data preparation, prepare wav.scp/text/utt2spk/spk2utt"
for x in train-clean-100 train-clean-360 train-other-500 dev-clean dev-other test-clean test-other; do
mkdir -p data/$x
python local/prepare_data.py --src_dir $data_dir/LibriTTS/$x --des_dir data/$x --instruct
# NOTE in CosyVoice3, we add instruct in sequence
python local/prepare_data.py --src_dir $data_dir/LibriTTS/$x --des_dir data/$x --instruct "You are a helpful assistant.<|endofprompt|>"
done
fi