这是zhtts作者推荐的TTS：
安装使用步骤
1. 创建Python 3.11环境
conda create -y -name paddle python=3.11
conda activate paddle2. 安装PaddlePaddle框架
python -m pip install paddlepaddle==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/3. 安装PaddleSpeech
git clone https://github.com/PaddlePaddle/PaddleSpeech.git
cd PaddleSpeech
pip install pytest-runner
pip install .4. 回滚一个包版本，否则会运行报错：ImportError: cannot import name 'download' from 'aistudio_sdk.hub'
pip install aistudio-sdk==0.2.65. 运行
paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav粤语安装使用步骤
6. 初始化环境
cd examples/canton/tts3
source path.sh7. 下载预训练模型
wget https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_canton_ckpt_1.4.0.zip
unzip fastspeech2_canton_ckpt_1.4.0.zip
wget https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip
unzip pwg_aishell3_ckpt_0.5.zip8. 运行测试
python3 ${BIN_DIR}/../synthesize_e2e.py --am=fastspeech2_aishell3 --am_config=fastspeech2_canton_ckpt_1.4.0/default.yaml --am_ckpt=fastspeech2_canton_ckpt_1.4.0/snapshot_iter_140000.pdz --am_stat=fastspeech2_canton_ckpt_1.4.0/speech_stats.npy --voc=pwgan_aishell3 --voc_config=pwg_aishell3_ckpt_0.5/default.yaml --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy --lang=canton --text=${BIN_DIR}/../../assets/sentences_canton.txt --output_dir=exp/default/test_e2e --phones_dict=fastspeech2_canton_ckpt_1.4.0/phone_id_map.txt --speaker_dict=fastspeech2_canton_ckpt_1.4.0/speaker_id_map.txt --spk_id=10 --inference_dir=exp/default/inference --ngpu=0参考：https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/canton/tts3
评论