FICHA · AUR

deepspeech-models

A TensorFlow implementation of Baidu's DeepSpeech architecture - models and supporting files.

  • Data
  • AUDIO
  • Dev
official+codex · reviewed · May 31, 2026 description in en

Description

Speech-recognition models and supporting files become available for DeepSpeech-based tools. They are useful when a transcription command or application needs ready model data to convert audio into text.

This package contains data, not an app. Models can be large, language-specific, and imperfect; recognition results still need review when accuracy matters.

Permissions

Permissions not analysed for this source yet.