pip install virtualenv
virtualenv -p python3 $HOME/opt/deepspeech/
source $HOME/opt/deepspeech/bin/activate
pip3 install deepspeech
pip3 install --upgrade deepspeech
pip3 install deepspeech-gpu ##for supported nvidia gpu +cuda
python3 -m pip install deepspeech --user
see https://github.com/mozilla/DeepSpeech/releases for updated links
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.scorer
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.pbmm
##for input via microphone
git clone https://github.com/mozilla/DeepSpeech-examples --depth=1
for deps https://github.com/mozilla/DeepSpeech-examples/tree/r0.9/vad_transcriber
sudo xbps-install portaudio-devel [
debian:portaudio19-dev, archlinux has devel files in portaudio]
pip install -r requirements.txt
#cmd to run via microphone
python ~/opt/deepspeech/
DeepSpeech-examples/
mic_vad_streaming/mic_vad_streaming.py -m ~/opt/deepspeech/deepspeech-0.9.3-models.pbmm -s ~/opt/deepspeech/deepspeech-0.9.3-models.scorer
for anaconda
conda install deepspeech [available from condaforge]
contribute voice
https://commonvoice.mozilla.org/en
https://commonvoice.mozilla.org/en/datasets
conclusion:
not working for my voice
sourcces::
https://github.com/mozilla/DeepSpeech-examples/tree/r0.9/vad_transcriber
https://github.com/mozilla/DeepSpeech/
https://deepspeech.readthedocs.io/en/r0.9/
Comments
Post a Comment