aguang-xyz / auto-caption Goto Github PK

I get the error message below, when I run auto-caption:

File "/Library/Frameworks/Python.framework/Versions/3.9/bin/auto-caption", line 7, in
main()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/auto_caption/init.py", line 226, in main
auto_caption(args.video, output, fmt=fmt, lang="en")
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/auto_caption/init.py", line 199, in auto_caption
sentences = segment_setences(words)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/auto_caption/init.py", line 119, in segment_setences
splits = NNSplit.load(lang).split([content])
AttributeError: type object 'NNSplit' has no attribute 'load'

I as using this to add subtitiles to my online lecture. However I was unable to add them into our insititutions transcript editor, with it complaining about a bad format. I ran the VTT generated here though an online VTT validator here and learned that miliseconds should be 3 digits long.

Just changing this line

To the following seems to fix this millisecond issue.

def time2str_vtt(x):

    return "{hour:02d}:{minute:02d}:{second:02d}.{millisecond:03d}".format(
        hour=int(x) // 3600,
        minute=(int(x) // 60) % 60,
        second=int(x) % 60,
        millisecond=int(x * 1000) % 1000)

It's a good idea to add the flag --language and support also other lang.
Thank you

Right after moviePy reports done I get the following (MacOS 10.15.7)

Traceback (most recent call last): File "/usr/local/bin/auto-caption", line 7, in <module> main() File "/usr/local/lib/python3.8/site-packages/auto_caption/__init__.py", line 226, in main auto_caption(args.video, output, fmt=fmt, lang="en") File "/usr/local/lib/python3.8/site-packages/auto_caption/__init__.py", line 199, in auto_caption sentences = segment_setences(words) File "/usr/local/lib/python3.8/site-packages/auto_caption/__init__.py", line 119, in segment_setences for tokens2d in tqdm(nnsplit.NNSplit(lang).split([content])): File "backend.py", line 5, in create_session File "/usr/local/lib/python3.8/site-packages/onnxruntime/capi/session.py", line 195, in __init__ self._create_inference_session(providers, provider_options) File "/usr/local/lib/python3.8/site-packages/onnxruntime/capi/session.py", line 200, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.NoSuchFile: [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from en failed:Load model en failed. File doesn't exist

latest vosk,onnxruntime, and nnsplit via pip3. libbomp via homebrew. attempted pip install of kaldi-active-grammar and dragonfly[kalidi] afterwards with no effect. ~/.auto-captions/models/en/... was created from zip download on the first run of the program. Apologies if I'm missing something obvious, new area for me.