Paddlespeech 语音识别与语音合成

conda create -n paddlespeech python=3.10
conda activate paddlespeech
# 下载依赖
pip install -r requirements.txt # 内容见下文
# 下载PadlleSpeech
git clone https://github.com/PaddlePaddle/PaddleSpeech.git
cd PaddleSpeech
# 对于到我写这一篇博客的当前版本来说，不用这个版本会报错，虽然其他会不会我不知道，但是这个不会
# 当前版本似乎要指定模型
git checkout 1b8ca706d6a8e0a8b97ee21d93314a245d777a69
pip install .
# 下载 Paddlepaddle
pip install paddlepaddle==2.6.0 -i https://mirror.baidu.com/pypi/simple
# 如果要用GPU就用下面的版本
# python -m pip install paddlepaddle-gpu==2.6.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
# 下载测试音频
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav

absl-py==2.0.0
aiohttp==3.9.1
aiosignal==1.3.1
aistudio-sdk==0.1.5
annotated-types==0.6.0
antlr4-python3-runtime==4.9.3
anyio==4.2.0
astor==0.8.1
asttokens==2.4.1
async-timeout==4.0.3
attrs==23.2.0
audioread==3.0.1
Babel==2.14.0
backcall==0.2.0
bce-python-sdk==0.8.99
blinker==1.7.0
bokeh==3.1.1
boltons==23.1.1
Bottleneck==1.3.7
braceexpand==0.1.7
certifi==2023.11.17
cffi==1.16.0
charset-normalizer==3.3.2
click==8.1.7
colorama==0.4.6
coloredlogs==15.0.1
colorlog==6.8.0
contourpy==1.1.1
cycler==0.12.1
Cython==3.0.8
datasets==2.16.1
decorator==5.1.1
dill==0.3.4
Distance==0.1.3
editdistance==0.6.2
einops==0.7.0
exceptiongroup==1.2.0
executing==2.0.1
fastapi==0.109.0
filelock==3.13.1
Flask==3.0.0
flask-babel==4.0.0
flatbuffers==23.5.26
fonttools==4.47.2
frozenlist==1.4.1
fsspec==2023.10.0
ftfy==6.1.3
future==0.18.3
g2p-en==2.1.0
g2pM==0.1.2.5
h11==0.14.0
h5py==3.10.0
httpcore==1.0.2
httpx==0.26.0
huggingface-hub==0.20.2
humanfriendly==10.0
HyperPyYAML==1.2.2
idna==3.6
importlib-metadata==7.0.1
importlib-resources==6.1.1
inflect==7.0.0
intervaltree==3.1.0
ipython==8.12.3
itsdangerous==2.1.2
jedi==0.19.1
jieba==0.42.1
Jinja2==3.1.3
joblib==1.3.2
jsonlines==4.0.0
kaldiio==2.18.0
kiwisolver==1.4.5
librosa==0.8.1
llvmlite==0.41.1
loguru==0.7.2
lxml==5.1.0
markdown-it-py==3.0.0
MarkupSafe==2.1.3
matplotlib==3.7.4
matplotlib-inline==0.1.6
mdurl==0.1.2
mido==1.3.2
mock==5.1.0
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.12.2
nara-wpe==0.0.9
nltk==3.8.1
note-seq==0.0.5
numba==0.58.1
numpy==1.23.5
omegaconf==2.3.0
onnx==1.15.0
onnxruntime==1.16.3
OpenCC==1.1.7
opencc-python-reimplemented==0.1.7
opencv-python==4.6.0.66
opt-einsum==3.3.0
packaging==23.2
paddle2onnx==1.1.0
paddleaudio==1.1.0
paddlefsl==1.1.0
paddlenlp==2.7.1
paddlepaddle==2.6.0
paddlesde==0.2.5
paddleslim==2.6.0
paddlespeech-ctcdecoders==0.2.1
paddlespeech-feat==0.1.0
pandas==2.0.3
parameterized==0.9.0
parso==0.8.3
pathos==0.2.8
pattern-singleton==1.2.0
pexpect==4.9.0
pickleshare==0.7.5
pillow==10.2.0
platformdirs==4.1.0
pooch==1.8.0
portalocker==2.8.2
pox==0.3.3
ppdiffusers==0.19.4
ppft==1.7.6.7
praatio==5.1.1
pretty-midi==0.2.10
prettytable==3.9.0
prompt-toolkit==3.0.43
protobuf==4.25.2
psutil==5.9.7
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==14.0.2
pyarrow-hotfix==0.6
pybind11==2.11.1
pycparser==2.21
pycryptodome==3.20.0
pydantic==2.5.3
pydantic_core==2.14.6
pydub==0.25.1
Pygments==2.17.2
pygtrie==2.5.0
pyparsing==3.1.1
pypinyin==0.44.0
pypinyin-dict==0.7.0
pytest-runner==6.0.1
python-dateutil==2.8.2
pytz==2023.3.post1
pyworld==0.3.4
PyYAML==6.0.1
pyzmq==25.1.2
rarfile==4.1
regex==2023.12.25
requests==2.31.0
requests-mock==1.11.0
resampy==0.4.2
rich==13.7.0
ruamel.yaml==0.18.5
ruamel.yaml.clib==0.2.8
sacrebleu==2.4.0
safetensors==0.4.1
scikit-learn==1.3.2
scipy==1.10.1
sentencepiece==0.1.99
seqeval==1.2.2
six==1.16.0
sniffio==1.3.0
sortedcontainers==2.4.0
soundfile==0.12.1
stack-data==0.6.3
starlette==0.35.1
swig==4.1.1.post1
sympy==1.12
tabulate==0.9.0
TextGrid==1.5
threadpoolctl==3.2.0
timer==0.2.2
ToJyutping==0.2.1
tool-helpers==0.1.1
tornado==6.4
tqdm==4.66.1
traitlets==5.14.1
trampoline==0.1.2
typeguard==2.13.3
typer==0.9.0
typing_extensions==4.9.0
tzdata==2023.4
urllib3==1.26.18
uvicorn==0.25.0
visualdl==2.5.3
wcwidth==0.2.13
webrtcvad==2.0.10
websockets==12.0
Werkzeug==3.0.1
xxhash==3.4.1
xyzservices==2023.10.1
yacs==0.1.8
yarl==1.9.4
zhon==2.0.2
zipp==3.17.0

import time

from paddlespeech.cli.asr.infer import ASRExecutor
asr = ASRExecutor()
result = asr(audio_file="4.wav", force_yes=True)
print(result)

start_time = time.time()
result = asr(audio_file="zh.wav", force_yes=True)
print(result)
print("耗时:", time.time()-start_time)
# 耗时: 1.0136737823486328
# GPU版本耗时: 0.07937979698181152

from paddlespeech.cli.tts.infer import TTSExecutor
tts = TTSExecutor()
text = "今天大家都好开心啊, 好多人啊"
tts(text=text, output='./output.wav')

import time
start_time = time.time()
tts(text="你好啊, 我是一个大西瓜, 怎么称呼你呢", output='./watermelon.wav')
print("耗时:", time.time()-start_time)
# 耗时: 1.1994433403015137
# GPU版本耗时: 0.14627718925476074

pip install scipy==1.11.4
# 之前是 1.13.0

import paddle
paddle.device.set_device('gpu:1')