Hi. I’m using Orin NX 16GB.
When I tried to run TTS example from Paddlespeech, an error was thrown.
>>> from paddlespeech.cli.tts import TTSExecutor
/home/nvidia/.local/lib/python3.8/site-packages/setuptools/sandbox.py:13: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
import pkg_resources
/home/nvidia/.local/lib/python3.8/site-packages/pkg_resources/__init__.py:2871: DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('mpl_toolkits')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
/home/nvidia/.local/lib/python3.8/site-packages/pkg_resources/__init__.py:2871: DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('google')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
/home/nvidia/.local/lib/python3.8/site-packages/librosa/core/constantq.py:1059: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
dtype=np.complex,
/home/nvidia/.local/lib/python3.8/site-packages/_distutils_hack/__init__.py:33: UserWarning: Setuptools is replacing distutils.
warnings.warn("Setuptools is replacing distutils.")
>>> tts_executor = TTSExecutor()
>>> wav_file = tts_executor(
... text="热烈欢迎您在 Discussions 中提交问题，并在 Issues 中指出发现的 bug。此外，我们非常希望您参与到 Paddle Speech 的开发中！",
... output='output.wav',
... am='fastspeech2_mix',
... voc='hifigan_csmsc',
... lang='mix',
... spk_id=174)
[2023-08-11 10:02:31,659] [ INFO] - Already cached /home/nvidia/.paddlenlp/models/bert-base-chinese/bert-base-chinese-vocab.txt
[2023-08-11 10:02:31,673] [ INFO] - tokenizer config file saved in /home/nvidia/.paddlenlp/models/bert-base-chinese/tokenizer_config.json
[2023-08-11 10:02:31,673] [ INFO] - Special tokens file saved in /home/nvidia/.paddlenlp/models/bert-base-chinese/special_tokens_map.json
W0811 10:02:34.054011 2760973 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 8.7, Driver API Version: 11.4, Runtime API Version: 11.4
W0811 10:02:34.065198 2760973 gpu_resources.cc:91] device: 0, cuDNN Version: 8.6.
Building prefix dict from the default dictionary ...
[2023-08-11 10:02:37] [DEBUG] [__init__.py:113] Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
[2023-08-11 10:02:37] [DEBUG] [__init__.py:132] Loading model from cache /tmp/jieba.cache
Loading model cost 0.956 seconds.
[2023-08-11 10:02:38] [DEBUG] [__init__.py:164] Loading model cost 0.956 seconds.
Prefix dict has been built successfully.
[2023-08-11 10:02:38] [DEBUG] [__init__.py:166] Prefix dict has been built successfully.
terminate called after throwing an instance of 'thrust::system::system_error'
what(): after determining tmp storage requirements for inclusive_scan: cudaErrorInvalidDeviceFunction: invalid device function
Aborted (core dumped)
Could you help analyse the cause of this? Thanks in advance.