尝试musicgen模型，torchaudio Failed to load audio from

最新推荐文章于 2024-02-06 17:28:29 发布

nangua06

最新推荐文章于 2024-02-06 17:28:29 发布

阅读量735

点赞数 7

文章标签： linux python 算法

本文链接：https://blog.csdn.net/nangua06/article/details/135083981

版权

Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/data/miniconda3/envs/musicgen/lib/python3.9/site-packages/torchaudio/backend/sox_io_backend.py", line 256, in load
return _fallback_load(filepath, frame_offset, num_frames, normalize, channels_first, format)
File "/data/miniconda3/envs/musicgen/lib/python3.9/site-packages/torchaudio/backend/sox_io_backend.py", line 30, in _fail_load
raise RuntimeError("Failed to load audio from {}".format(filepath))
RuntimeError: Failed to load audio from ./assets/bach.mp3

原因：

Starting 0.12, the MP3 decoder is switched to libavcodec. The error indicates that there is no installation of FFmpeg 4. Please install ffmpeg 4. conda install 'ffmpeg<5' should do in most cases.

解决方式：
conda install 'ffmpeg<5'