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.
Mozilla Public License 2.0
25.29k stars 3.96k forks source link

Running deepspeech- KeyError , TypeError, frozen graph #1233

Closed alughaGmbH closed 6 years ago

alughaGmbH commented 6 years ago

Hi all,

I am following https://github.com/mozilla/DeepSpeech/blob/master/native_client/README.md to use Deepspeech. I am not able to advance. kindly clear my points. It will be a great help.

Issues

1) When I am trying to train my model, the corpus which I downloaded do not have wav_filesize column in the CSV file . So it gives me KeyError: 'wav_filesize' . 2) I have a audio file which I am trying to run with Deepspeech- it gives me TypeError: Cannot cast array data from dtype('float32') to dtype('int16') according to the rule 'safe' 3) If I want to train my model further, we have Continuing training from a frozen graph option. But I am not so clear how this is working. I can I continue with this. 4) The audio file which I used was a 2-Dimensional it tells. So now how can I conver it into 1 dimensional. TypeError: Array must have 1 dimensions. Given array has 2 dimensions

Thank you, Alugha

alughaGmbH commented 6 years ago

I also checked Handling audio with more than one channel? #675 . But this could not help me.

lissyx commented 6 years ago

@alughaGmbH Thanks, however:

lock[bot] commented 5 years ago

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.