PaddlePaddle / PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
https://paddlespeech.readthedocs.io
Apache License 2.0
11.21k stars 1.86k forks source link

[TTS] 使用paddle 2.5.1版本时 transformer tts 模型推理有问题 #3563

Open layne01291 opened 1 year ago

layne01291 commented 1 year ago
  1. transformer tts
  2. 使用paddle2.4.2+(develop or r1.4.1),进行transformer tts预训练模型推理的结果语音正常
  3. 使用paddle2.5.1+(develop or 1.4.1),进行transformer tts预训练模型推理的结果语音非正常(发音不清楚,断断续续) 不清楚是不是paddlespeech没有适配到2.5.1版本还是其他问题

环境:

Package                     Version
--------------------------- ---------------
absl-py                     2.0.0
aiohttp                     3.8.5
aiosignal                   1.3.1
annotated-types             0.5.0
antlr4-python3-runtime      4.9.3
anyio                       3.7.1
aspy.yaml                   1.3.0
astor                       0.8.1
astroid                     2.12.10
async-timeout               4.0.3
asynctest                   0.13.0
attrs                       22.1.0
audioread                   3.0.1
Babel                       2.12.1
bce-python-sdk              0.8.87
bokeh                       2.4.3
boltons                     23.0.0
Bottleneck                  1.3.7
cached-property             1.5.2
certifi                     2022.9.14
cffi                        1.15.1
cfgv                        3.3.1
charset-normalizer          2.1.1
click                       8.1.4
colorama                    0.4.6
coloredlogs                 15.0.1
colorlog                    6.7.0
cycler                      0.11.0
Cython                      3.0.3
datasets                    2.13.2
decorator                   5.1.1
dill                        0.3.4
Distance                    0.1.3
distlib                     0.3.6
editdistance                0.6.2
einops                      0.6.1
entrypoints                 0.4
et-xmlfile                  1.1.0
exceptiongroup              1.1.3
fastapi                     0.103.1
filelock                    3.8.0
Flask                       2.2.5
flask-babel                 3.1.0
flatbuffers                 23.5.26
fonttools                   4.38.0
frozenlist                  1.3.3
fsspec                      2023.1.0
ftfy                        6.1.1
future                      0.18.3
g2p-en                      2.1.0
g2pM                        0.1.2.5
h11                         0.14.0
h5py                        3.8.0
httpcore                    0.17.3
httpx                       0.24.1
huggingface-hub             0.16.4
humanfriendly               10.0
HyperPyYAML                 1.2.2
identify                    2.5.5
idna                        3.4
importlib-metadata          4.12.0
inflect                     6.0.5
iniconfig                   1.1.1
intervaltree                3.1.0
ipykernel                   4.6.0
ipython                     5.3.0
isort                       5.10.1
itsdangerous                2.1.2
jieba                       0.42.1
Jinja2                      3.1.2
joblib                      1.3.1
jsonlines                   3.1.0
jupyter_client              7.3.5
jupyter-core                4.11.1
kaldiio                     2.18.0
kiwisolver                  1.4.4
lazy-object-proxy           1.7.1
librosa                     0.8.1
llvmlite                    0.39.1
loguru                      0.7.2
lxml                        4.9.3
markdown-it-py              2.2.0
MarkupSafe                  2.1.3
matplotlib                  3.5.3
mccabe                      0.7.0
mdurl                       0.1.2
mido                        1.3.0
mock                        5.1.0
mpmath                      1.3.0
multidict                   6.0.4
multiprocess                0.70.12.2
nara-wpe                    0.0.9
nest-asyncio                1.5.5
nltk                        3.8.1
nodeenv                     1.7.0
note-seq                    0.0.3
numba                       0.56.4
numpy                       1.21.6
omegaconf                   2.3.0
onnx                        1.14.1
onnxruntime                 1.14.1
OpenCC                      1.1.6
opencc-python-reimplemented 0.1.7
opencv-python               4.5.5.64
openpyxl                    3.1.2
opt-einsum                  3.3.0
packaging                   23.2
paddle-bfloat               0.1.7
paddle2onnx                 1.0.9
paddleaudio                 1.1.0
paddlefsl                   1.1.0
paddlenlp                   2.6.0
paddlepaddle-gpu            2.5.1.post117
paddlesde                   0.2.5
paddleseg                   2.8.0
paddleslim                  2.4.1
paddlespeech                1.4.1
paddlespeech-ctcdecoders    0.2.1
paddlespeech-feat           0.1.0
pandas                      1.3.5
parameterized               0.9.0
pathos                      0.2.8
pattern-singleton           1.2.0
pexpect                     4.8.0
pickleshare                 0.7.5
Pillow                      9.2.0
pip                         22.3.1
platformdirs                2.5.2
pluggy                      1.0.0
pooch                       1.7.0
portalocker                 2.7.0
pox                         0.3.3
ppdiffusers                 0.19.3
ppft                        1.7.6.7
praatio                     5.1.1
pre-commit                  1.10.4
pretty-midi                 0.2.10
prettytable                 3.7.0
prompt-toolkit              1.0.18
protobuf                    4.24.4
psutil                      5.9.5
ptyprocess                  0.7.0
py                          1.11.0
pyarrow                     12.0.1
pybind11                    2.11.1
pycparser                   2.21
pycryptodome                3.18.0
pydantic                    1.10.13
pydantic_core               2.6.3
pydub                       0.25.1
Pygments                    2.13.0
PyGObject                   3.26.1
pygtrie                     2.5.0
pylint                      2.15.3
pyparsing                   3.0.9
pypinyin                    0.44.0
pypinyin-dict               0.6.0
pytest                      7.1.3
pytest-runner               6.0.0
python-apt                  1.6.5+ubuntu0.7
python-dateutil             2.8.2
pytz                        2023.3
pyworld                     0.3.4
PyYAML                      6.0
pyzmq                       24.0.1
rarfile                     4.0
regex                       2023.10.3
requests                    2.28.1
requests-mock               1.11.0
resampy                     0.4.2
rich                        13.5.2
ruamel.yaml                 0.17.35
ruamel.yaml.clib            0.2.8
sacrebleu                   2.3.1
safetensors                 0.3.3
scikit-learn                1.0.2
scipy                       1.7.3
sentencepiece               0.1.99
seqeval                     1.2.2
setuptools                  50.3.2
setuptools-scm              7.1.0
simplegeneric               0.8.1
six                         1.16.0
sniffio                     1.3.0
sortedcontainers            2.4.0
soundfile                   0.12.1
starlette                   0.27.0
swig                        4.1.1
sympy                       1.10.1
tabulate                    0.9.0
TextGrid                    1.5
threadpoolctl               3.1.0
timer                       0.2.2
ToJyutping                  0.2.3
toml                        0.10.2
tomli                       2.0.1
tomlkit                     0.11.4
tornado                     6.2
tqdm                        4.65.0
traitlets                   5.4.0
trampoline                  0.1.2
typed-ast                   1.5.4
typeguard                   2.13.3
typer                       0.9.0
typing_extensions           4.7.1
unattended-upgrades         0.1
urllib3                     1.26.12
uvicorn                     0.22.0
virtualenv                  20.16.5
visualdl                    2.5.3
wcwidth                     0.2.5
webrtcvad                   2.0.10
websockets                  11.0.3
Werkzeug                    2.2.3
wheel                       0.37.1
wrapt                       1.14.1
xxhash                      3.3.0
yacs                        0.1.8
yarl                        1.9.2
zhon                        2.0.2
zipp                        3.8.1
JiadiLee commented 10 months ago

我现在用develop版本,paddle==2.5.1,am='fastspeech2_aishell3', voc='hifigan_aishell3'进行语音推理,也是存在非常不清楚,且断续的问题,在paddle==2.4.2的情况下正常,请问您这个问题解决了吗?