[WinError 2] The system cannot find the file specified

[pandalay1]

WARNING: F5TTSAudioInputs.IS_CHANGED() got an unexpected keyword argument 'model'
Converting audio...
F5TTS: Cannot remove? C:\Users*\AppData\Local\Temp\tmpkzgpj26j.wav
[WinError 32] The process cannot access the file because it is being used by another process: 'C:\Users\*\AppData\Local\Temp\tmpkzgpj26j.wav'
!!! Exception during processing !!! [WinError 2] The system cannot find the file specified

[niknah]

It should still work. Did you get the audio output?
I don't know why, it won't remove the temp file even though it has finished using it.

[pandalay1]

No, generation stops after this error. Full log below.

got prompt
WARNING: F5TTSAudioInputs.IS_CHANGED() got an unexpected keyword argument 'model'
Converting audio...
F5TTS: Cannot remove? C:\Users\panda\AppData\Local\Temp\tmprl15676t.wav
[WinError 32] The process cannot access the file because it is being used by another process: 'C:\Users\panda\AppData\Local\Temp\tmprl15676t.wav'
!!! Exception during processing !!! [WinError 2] The system cannot find the file specified
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\custom_nodes\ComfyUI-F5-TTS\F5TTS.py", line 210, in create
main_voice = self.load_voice_from_input(sample_audio, sample_text)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\custom_nodes\ComfyUI-F5-TTS\F5TTS.py", line 196, in load_voice_from_input
r = F5TTSCreate.load_voice(self.wave_file.name, sample_text)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\custom_nodes\ComfyUI-F5-TTS\F5TTS.py", line 53, in load_voice
main_voice["ref_audio"], main_voice["ref_text"] = preprocess_ref_audio_text( # noqa E501
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\custom_nodes\ComfyUI-F5-TTS\F5-TTS\model\utils_infer.py", line 146, in preprocess_ref_audio_text
aseg = AudioSegment.from_file(ref_audio_orig)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\python_embeded\Lib\site-packages\pydub\audio_segment.py", line 728, in from_file
info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nightly_pytorch\python_embeded\Lib\site-packages\pydub\utils.py", line 274, in mediainfo_json
res = Popen(command, stdin=stdin_parameter, stdout=PIPE, stderr=PIPE)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "subprocess.py", line 1026, in init
File "subprocess.py", line 1538, in _execute_child
FileNotFoundError: [WinError 2] The system cannot find the file specified

Prompt executed in 0.05 seconds

[niknah]

It might not have made the audio from the input. I have put an error message there. Can you update it and run it again. Where which node does the sample audio input come from and can you play it in "preview audio"