使用英伟达jeston orin nano遇到的问题

[TigerHH6866]

最近尝试使用英伟达jeston orin nano测试项目
NVIDIA Jetson Orin NX Engineering Reference Developer Kit
Package: nvidia-l4t-core
Version: 36.4.0-20240912212859
cuda 12.6

启动：python .\app.py --avatar_id model01_720 --models wav2lip --tts edgetts --listenport 8010

human发送文本推理时报错：
Exception in thread Thread-2 (process_tts):
Traceback (most recent call last):
File "/home/aiyo/avatarhuman/avatarhuman/venv/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/home/aiyo/avatarhuman/avatarhuman/venv/lib/python3.10/threading.py", line 953, in run
self._target(self._args, **self._kwargs)
File "/home/aiyo/avatarhuman/avatarhuman/ttsreal.py", line 71, in process_tts
self.txt_to_audio(msg)
File "/home/aiyo/avatarhuman/avatarhuman/ttsreal.py", line 91, in txt_to_audio
stream = self.__create_bytes_stream(self.input_stream)
File "/home/aiyo/avatarhuman/avatarhuman/ttsreal.py", line 105, in __create_bytes_stream
stream, sample_rate = sf.read(byte_stream) # [Tsample_rate,] float64
File "/home/aiyo/avatarhuman/avatarhuman/venv/lib/python3.10/site-packages/soundfile.py", line 285, in read
with SoundFile(file, 'r', samplerate, channels,
File "/home/aiyo/avatarhuman/avatarhuman/venv/lib/python3.10/site-packages/soundfile.py", line 658, in init
self._file = self._open(file, mode_int, closefd)
File "/home/aiyo/avatarhuman/avatarhuman/venv/lib/python3.10/site-packages/soundfile.py", line 1216, in _open
raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening <_io.BytesIO object at 0xffff12dd4590>: Format not recognised.

[cacard]

这个能流畅运行吗？。。。期待你的结果。

[TigerHH6866]

这个能流畅运行吗？。。。期待你的结果。

16fps,不流畅

[cacard]

这个能流畅运行吗？。。。期待你的结果。

16fps,不流畅

期待你优化到24fps —— :)