Mozilla's DeepSpeech transcriber in a pip installable package.
Project description
pydeepspeech
- The simpliest way to use AI to generate transcriptions from a wav file.
- This project uses the Mozilla DeepSpeech engine built from the included demo:
Quick start
Install to current python environment
Console api:
$ pip install pydeepspeech
$ pydeepspeech --wav_file <WAVE_FILE> --aggressive 1 --out_file <TEXT_FILE>
-or-
$ pydeepspeech --wav_file <WAVE_FILE> --out_file <TEXT_FILE> --model_dir <MY_PBMM_AND_SCORER_FILES>
-or-
$ pydeepspeech_installmodels --pbmm <PBMM_FILE_OR_URL> --scorer <SCORER_FILE_OR_URL>
$ pydeepspeech --wav_file <WAVE_FILE> --out_file <TEXT_FILE>
Or in python
from pydeepspeech.transcribe import transcribe
transcribe(...)
Optional: Create a virtual python package
Download and install virtual env:
# Download
curl -X GET https://raw.githubusercontent.com/zackees/make_venv/main/make_venv.py -o make_env.py
python make_env.py # Make the environment
source activate.sh # Enter environment
pip install -e .
To get back into the environment execute source activate.sh
(if windows, you must be using git-bash)
Testing
Testing and linting is very simple. Just run tox
$ tox
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pydeepspeech-1.1.6.tar.gz
(10.6 kB
view hashes)
Built Distribution
Close
Hashes for pydeepspeech-1.1.6-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0366a2c41e9866ded96cf1f8a4952e828bfc05b9f58d612c0143057d1a71693a |
|
MD5 | d8ea2140fa3be74168b4d2c1373166ce |
|
BLAKE2b-256 | ec3c710d7d5816a5f0b88fa5b7452e037513fc806e8ce74bc03e9ef9ee389586 |