未验证 提交 ffdc17fd 编写于 作者: 小湉湉's avatar 小湉湉 提交者: GitHub

Update voice_cloning.sh

上级 05353b6c
...@@ -5,8 +5,6 @@ train_output_path=$2 ...@@ -5,8 +5,6 @@ train_output_path=$2
ckpt_name=$3 ckpt_name=$3
ref_audio_dir=$4 ref_audio_dir=$4
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 ${BIN_DIR}/../voice_cloning.py \ python3 ${BIN_DIR}/../voice_cloning.py \
--am=fastspeech2_aishell3 \ --am=fastspeech2_aishell3 \
--am_config=${config_path} \ --am_config=${config_path} \
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册