How can deepspeech show progress when transcribing?

Archives DeepSpeech
#1

I have installed it using these instructions:

Create and activate a virtualenv

virtualenv -p python3 $HOME/tmp/deepspeech-venv/
source $HOME/tmp/deepspeech-venv/bin/activate

Install DeepSpeech

pip3 install deepspeech

Download pre-trained English model files

curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.pbmm
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.scorer

Download example audio files

curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/audio-0.9.3.tar.gz
tar xvf audio-0.9.3.tar.gz

Transcribe an audio file

deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/2830-3980-0043.wav

Running the following command does not show progress:

deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/output.wav > output.txt

And this other command gives an error:

deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/output.wav --json --log_level 0 > output.txt

“deepspeech: error: unrecognized arguments: --log_level 0”

#2

What are you running inference on?
How long is the audio file?

log_level is not a command line argument for the deepspeech binary.

1 Like
#3

It is an 285MB wav. I cant tell what is happening after I run the command, that is why I would like to see verbose output, but how can that be done?:
deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/output.wav > output.txt

1 Like
#4

Please understand the project is not maintained anymore and the deepspeech binary is just a quick example of how to use the lib. You could use streaming interface to handle a progressbar.