Giters

mozilla / DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Repository from Github https://github.commozilla/DeepSpeechRepository from Github https://github.commozilla/DeepSpeech

Why I call DS_IntermediateDecode always crash a few seconds later at the iphone device?

czwldy opened this issue · comments

commented

For support and discussions, please use our Discourse forums.

If you've found a bug, or have a feature request, then please create an issue with the following information:

  • iOS system, iphone:
  • TensorFlow version (use command below):
  • Python version:
  • Bazel version bazel-3.1.0:
  • GCC/Compiler version C++14:
  • set bean_width = 1 and use master branch code:
                stream!.feedAudioContent(buffer: shorts)
                print("czwxx\(byteSize):\(stream!.intermediateDecode())")  // I add the code here, at the SpeechRecognitionImpl class.

At the swift demo, I add stream!.intermediateDecode() after stream!.feedAudioContent(buffer: shorts), it would crash EXC_BAD_ACCESS (code=2, address=0x16e023ff0) at the function get_history_helper a few seconds later.

commented

To analyze syllables or phonemes alongside DeepSpeech, consider integrating with libraries like NLTK or PyDictionary in Python. These libraries provide syllable information and phonetic details, complementing DeepSpeech's text-to-speech conversion. By combining these tools, you can create a comprehensive solution for a more in-depth linguistic analysis of spoken words.