AssertionError

[philipperemy]

AssertionError

[InSightSuen]

the VCTK_CORPUS_PATH should be like "*/VCTK-Corpus/wav48"

[philipperemy]

@InSightSuen thanks for answering :)

[ccpyo]

Thanks a lot, but I have another question for it.I make it have the correct datapath, but it shows another error now.It doesn't make any cache file in that directory.Did I miss any step with that?

C:\Users\OAQ\ctc-speech>python generate_audio_cache.py
{'AUDIO': {'SAMPLE_RATE': 8000, 'VCTK_CORPUS_PATH': '/tmp/p225/wav48/'}}
Initializing AudioReader()
audio_dir = /tmp/p225/wav48/
sample_rate = 8000
speakers_sub_list = ['p225']
Nothing found at /tmp/tensorflow-ctc-speech-recognition/. Generating all the caches now.
Found 231 files in total in /tmp/p225/wav48/.
231 files correspond to the speaker list ['p225'].
Traceback (most recent call last):
File "generate_audio_cache.py", line 18, in
generate()
File "generate_audio_cache.py", line 14, in generate
speakers_sub_list=speakers_sub_list)
File "C:\Users\OAQ\ctc-speech\audio_reader.py", line 77, in init
with open(tmp_filename, 'wb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/tmp/tensorflow-ctc-speech-recognition/wav48\p225\p225_001_cache.pkl'

[philipperemy]

@ccpyo yes you have to generate the cache.

[philipperemy]

python3 generate_audio_cache.py

[philipperemy]

https://github.com/philipperemy/tensorflow-ctc-speech-recognition#how-to-get-started

[ccpyo]

I have already run that code, and that error message was occurred while I'm trying to generate the cache.

[philipperemy]

@ccpyo maybe because you're running on Windows.