Problem with large files

[test01203]

Hi, I tried to put a 2 GB movie in it, but it gets stuck in the middle and says an error
I tried several movies with the same glitch
I'd love for you to sort it out
I am working on Windows 11

[jhj0517]

Hi, I just tried to reproduce similar problem but failed.
But it's highly likely that the problem occurs from lack of GPU RAM or CPU performance.
So I recommend to use smaller model.
Or best approach would be to split the video into 2 or multiple files then proceed with transcribing each file separately.

[Tom-Neverwinter]

had this error then closed and re-opened, it took the file and processed it with no problem?

"Error transcribing file on line CUDA failed with error out of memory"

https://pastebin.com/wRVCpcep however my setup should have ample vram and system ram

finally caught it:

venv "C:\Users\Tom_N\Desktop\Whisper-WebUI\\venv\Scripts\Python.exe"
Use Faster Whisper implementation
Device "cuda" is detected
C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\components\dropdown.py:163: UserWarning: The value passed into gr.Dropdown() is not in the list of choices. Please update the list of choices to include: float16 or set allow_custom_value=True.
  warnings.warn(
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "C:\Users\Tom_N\miniconda3\lib\asyncio\events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
  File "C:\Users\Tom_N\miniconda3\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\torch\cuda\memory.py:330: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats.
  warnings.warn(
Error transcribing file on line 'NoneType' object is not iterable
Traceback (most recent call last):
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\queueing.py", line 495, in call_prediction
    output = await route_utils.call_process_api(
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
    output = await app.get_blocks().process_api(
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\blocks.py", line 1561, in process_api
    result = await self.call_function(
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\blocks.py", line 1179, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper
    response = f(*args, **kwargs)
  File "C:\Users\Tom_N\Desktop\Whisper-WebUI\modules\faster_whisper_inference.py", line 127, in transcribe_file
    self.remove_input_files([fileobj.name for fileobj in fileobjs])
TypeError: 'NoneType' object is not iterable
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "C:\Users\Tom_N\miniconda3\lib\asyncio\events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
  File "C:\Users\Tom_N\miniconda3\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host