Skip to content

Releases: mozilla/deepspeech-playbook

Continuous Integration now documented

28 Apr 22:52
4af2935
Compare
Choose a tag to compare

This release documents GitHub Actions for use where DeepSpeech is cloned to another repository - for example to work on a specific language.

v1.0

24 Mar 18:58
70ae194
Compare
Choose a tag to compare

This is the first stable release of the DeepSpeech PlayBook.

It has been updated from the Alpha version based on user feedback.

Feedback is warmly welcomed through raising an Issue.

  • Please try these instructions, particularly for building a Docker image and running a Docker container, on multiple distributions of Linux so that we can identify corner cases.

  • Please contribute your tacit knowledge - such as:
    - common errors encountered in data formatting, environment setup, training and validation
    - techniques or approaches for improving the scorer, alphabet file or the accuracy of Word Error Rate (WER) and Character Error Rate (CER).
    - case studies of the work you or your organisation have been doing, showing your approaches to data validation, training or evaluation.

    Please identify errors in text - with many eyes, bugs are shallow :-)

v0.1 Alpha release

09 Feb 00:37
2d7d18a
Compare
Choose a tag to compare
v0.1 Alpha release Pre-release
Pre-release

This is the very first public release of the DeepSpeech PlayBook 🎉

We warmly welcome your feedback, via raising an Issue, or via email to [email protected].

  • Please try these instructions, particularly for building a Docker image and running a Docker container, on multiple distributions of Linux so that we can identify corner cases.

  • Please contribute your tacit knowledge - such as:

    • common errors encountered in data formatting, environment setup, training and validation
    • techniques or approaches for improving the scorer, alphabet file or the accuracy of Word Error Rate (WER) and Character Error Rate (CER).
    • case studies of the work you or your organisation have been doing, showing your approaches to data validation, training or evaluation.
  • Please identify errors in text - with many eyes, bugs are shallow :-)