Wav2Vec2 STT Python

Beta Software

Simple Python library, distributed via binary wheels with few direct dependencies, for easily using wav2vec 2.0 models for speech recognition.

Requirements:

• Python 3.7+
• Platform: Linux x64 (Windows is a work in progress; MacOS may work; PRs welcome)
• Python package requirements: cffi, numpy
• Wav2Vec2 2.0 Model (must be converted to compatible format)
  • Several are available ready-to-go on this project's releases page and below.
  • You can convert your own models by following the instructions here.

Models:

Usage

from wav2vec2_stt import Wav2Vec2STT
decoder = Wav2Vec2STT('model_dir')

import wave
wav_file = wave.open('tests/test.wav', 'rb')
wav_samples = wav_file.readframes(wav_file.getnframes())

assert decoder.decode(wav_samples).strip().lower() == 'it depends on the context'

Also contains a simple CLI interface for recognizing wav files:

$ python -m wav2vec2_stt decode model test.wav
IT DEPENDS ON THE CONTEXT
$ python -m wav2vec2_stt decode model test.wav test.wav
IT DEPENDS ON THE CONTEXT
IT DEPENDS ON THE CONTEXT
$ python -m wav2vec2_stt -h
usage: python -m wav2vec2_stt [-h] {decode} ...

positional arguments:
  {decode}    sub-command
    decode    decode one or more WAV files

optional arguments:
  -h, --help  show this help message and exit

Installation/Building

Recommended installation via wheel from pip (requires a recent version of pip):

python -m pip install wav2vec2_stt

See setup.py for more details on building it yourself.

Author

• David Zurow (@daanzu)

License

This project is licensed under the GNU Affero General Public License v3 (AGPL-3.0-or-later). See the LICENSE file for details. If this license is problematic for you, please contact me.

Acknowledgments

• Contains and uses code from PyTorch and torchaudio, licensed under the BSD 2-Clause License.