音频降噪开头出现咳嗽声,降噪异常(UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 172: invalid start byte)

[abo123456789]

音频前面出现了咳嗽声音,点击降噪出现了如下错误:
Successfully loaded model.ckpt-59-3498143.pt for decoding
Traceback (most recent call last):
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\gradio\queueing.py", line 624, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\gradio\route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\gradio\blocks.py", line 2043, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\gradio\blocks.py", line 1590, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\anyio_backends_asyncio.py", line 2505, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\anyio_backends_asyncio.py", line 1005, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\py311_cu118\Lib\site-packages\gradio\utils.py", line 865, in wrapper
response = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "clear_app.py", line 28, in clear_app.fn_clearvoice_ss
File "E:\ClearVoice\ClearVoice\clearvoice.py", line 38, in call
result = model.process(input_path, online_write, output_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\networks.py", line 217, in process
data_reader = DataReader(self.args) # Initialize a data reader to load the audio files
^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\dataloader\dataloader.py", line 110, in init
self.file_list = read_and_config_file(args, args.input_path, decode=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ClearVoice\ClearVoice\dataloader\misc.py", line 67, in read_and_config_file
for line in fid:
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 172: invalid start byte

[alibabasglab]

你好，这个不是降噪模型的问题，是检测音频文件的时候出现误判，我们已经更新了代码，请使用最新代码。