# Create a virtualenv
python3 -m venev .
# Activate that
source bin/activate
# Install DeepSpeech
pip3 install deepspeech
# Download pre-trained English model files
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.pbmm
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.scorer

# Install Sox (for .wav file loading)
brew install sox
# Install NPM dependencies
npm install

# Transcribe an audio file
deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/lesson1.wav --json --extended > transcript_lesson1.txt

Audio

Convertí a 16000 muestras por segundo según lo requerido por deepspeech.