hay / audio2text Goto Github PK

After installing and trying to run it for the first time I get the error below:

Traceback (most recent call last): File "audio2text/./audio2text.py", line 50, in <module> whisper.transcribe(in_path, out_path) File "audio2text/audio2text/whisper.py", line 55, in transcribe self.transcribe_processed_wav(tmp_file, out_path) File "audio2text/audio2text/whisper.py", line 61, in transcribe_processed_wav str(self.whisper_path.resolve()), AttributeError: 'str' object has no attribute 'resolve'

The command I've used was:
./audio2text.py -w ../whisper.cpp/main -m ../whisper.cpp/models/ggml-tiny.bin -i test/berliner.og g -o test/berliner.csv -of csv

Am I overlooking something?

Using verbose as results in:

Initialized AudioToText Transcribing test/berliner.ogg as test/berliner.csv Converting test/berliner.ogg to tmp/jX85WfkYSMTfiqru4UTWEn.wav Traceback (most recent call last): File "audio2text/./audio2text.py", line 50, in <module> whisper.transcribe(in_path, out_path) File "audio2text/audio2text/whisper.py", line 55, in transcribe self.transcribe_processed_wav(tmp_file, out_path) File "audio2text/audio2text/whisper.py", line 61, in transcribe_processed_wav str(self.whisper_path.resolve()), AttributeError: 'str' object has no attribute 'resolve'

Using Python 3.10.6 on Ubuntu Linux 22.04.1