Skip to content

swayam01/ASR

Repository files navigation

ASR

Link to download Trained Model: https://drive.google.com/open?id=1ieYoLSIzin4uHL0QCo7KaAiHXVtBtXBf (unzip and place it inside this folder)

Install via pip

  • Python >= 3.6
  • Tensorflow = 1.14
  • Scipy (for reading wav files)

RUN mic.py

Limitations

  • The max duration of your audio file should be less than 15 seconds else an error will not be thrown if the duration exceeds and your transcript may contain errors and missing text.
  • Trained on english audio with Indian Accent recorded at 16 KHz

About

Trained Transformer model for Speech Recognition

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages