Replies: 1 comment 1 reply
-
This most likely mean you have an older version of the STT package which is trying to load a
Yeah I'm updating the examples for 1.0 right now. Basically as long as you have STT 1.0.0 installed you should be able to simply do: $ pip install -U pip
$ pip install stt
$ stt --model model.tflite --scorer scorer.scorer --audio audio.wav |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello! I'm trying to find an updated example of using the latest model to transcribe, well, any .wav file would be fine.
Places I've looked none of which seem to work:
RuntimeError: CreateModel failed with 'Error reading the proto buffer model file.' (0x3005)
, when I point it to themodel.tflite
file.wavTranscriber.py", line 61
, called from audioTranscript_cmd.py", line 37.tensorflow.compat
. Triedpip install -r requirements_transcribe.txt
, but if you look at that file (right here) it literally just haswebrtcvad
. If you try just installingpip install stt coqui_stt_training coqui_stt_ctcdecoder
you get this error:So to sum up: is there a clear, working, tested example, using the latest model, and with documented requirements?
Beta Was this translation helpful? Give feedback.
All reactions