https://paperswithcode.com/task/text-to-speech-synthesis

https://github.com/PaddlePaddle/PaddleSpeech

https://github.com/coqui-ai/TTS

https://github.com/keonlee9420/Expressive-FastSpeech2

https://github.com/TensorSpeech/TensorflowTTS

docker镜像：

https://hub.docker.com/r/paddlepaddle/paddle/tags/

docker run -it --gpus device=3 -v /ssd/xiedong/tts:/ssd/xiedong/tts --shm-size 16G paddlepaddle/paddle:2.5.1-gpu-cuda12.0-cudnn8.9-trt8.6 bashpython3.10 -m pip install --upgrade pipcd PaddleSpeech
pip install pytest-runner
pip install . -i https://pypi.tuna.tsinghua.edu.cn/simple

示例文件：

wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav

语音识别：

paddlespeech asr --lang zh --input zh.wav

语音合成：

paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav