DeepSpeech Is Discontinued (2020)

原始链接: https://github.com/mozilla/DeepSpeech

Status This project is now discontinued. Project DeepSpeech DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow to make the implementation easier. Documentation for installation, usage, and training models are available on deepspeech.readthedocs.io. For the latest release, including pre-trained models and checkpoints, see the latest release on GitHub. For contribution guidelines, see CONTRIBUTING.rst. For contact and support information, see SUPPORT.rst.

The Hacker News discussion revolves around the discontinuation of Mozilla's DeepSpeech project. A user points out the project was effectively discontinued years ago, despite the recent archive of the repository. Alternative news sources, like Phoronix, are suggested as better links, though some users criticize Phoronix's journalistic quality. One commenter theorizes that Google intentionally undermines Mozilla's innovation through funding and influence, keeping Firefox from becoming a true competitor. This is countered by arguments that Firefox's stagnation is due to a marketing deficit rather than a lack of innovation. The conversation then shifts to alternative speech-to-text (STT) models, with Nvidia's Parakeet being highlighted as a fast, albeit English-only option. Whisper is also mentioned, alongside smaller, distilled versions for resource-constrained devices. Piper is suggested as a CPU-friendly text-to-speech (TTS) option suitable for Raspberry Pi. Coqui-AI STT, a successor to DeepSpeech, recommends OpenAI's Whisper for STT needs. Finally, Festival is mentioned as a lightweight TTS option with basic voice quality.

Status

This project is now discontinued.

Project DeepSpeech

DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow to make the implementation easier.

Documentation for installation, usage, and training models are available on deepspeech.readthedocs.io.

For the latest release, including pre-trained models and checkpoints, see the latest release on GitHub.

For contribution guidelines, see CONTRIBUTING.rst.

For contact and support information, see SUPPORT.rst.