Stack Overflow
Stack Overflow

Questions tagged [mozilla-deepspeech]

Mozilla DeepSpeech is a TensorFlow implementation of Baidu's DeepSpeech architecture.

Code: https://github.com/mozilla/DeepSpeech

103 questions
1
vote
1 answer

How to check the number of parameters in Mozilla's DeepSpeech model?

I failed to find a simple way to print out how many parameters in the model and proposals to print it in release notes did not find the warm…
banderlog013
  • 2,207
  • 24
  • 33
1
vote
1 answer

Mozilla Deep Speech SST suddenly can't spell

I am using deep speech for speech to text. Up to 0.8.1, when I ran transcriptions like: byte_encoding = subprocess.check_output( "deepspeech --model deepspeech-0.8.1-models.pbmm --scorer deepspeech-0.8.1-models.scorer --audio…
Mittenchops
  • 18,633
  • 33
  • 128
  • 246
1
vote
2 answers

How to save transcript to a text file in Mozilla DeepSpeech?

This command is working and display the output However I could not find the command to save the output a text file What are my options? I want to generate text of speech to upload youtube video for subtitling (yes youtube algorithm failed to auto…
Furkan Gözükara
  • 22,964
  • 77
  • 205
  • 342
1
vote
3 answers

Increasing speak limit of mozilla tts

I am a beginner, I downloaded the model and tried studying it. But whenever I convert a sentence to speech, The model stops at 35 seconds or around 440 characters giving max_decoder_steps warning. I want to convert a story to speech which would be…
AmanSharma
  • 821
  • 9
  • 15
1
vote
1 answer

terminate called after throwing an instance of 'std::length_error' in Deepspeech

I am trying to decode a wav file after training a model from scratch, i finished the training and the testing phase without errors and I get the WER & CER and Loss values. NB: I’ve already done the decoding with this command with no errors but it…
Abir Messaoudi
  • 11
  • 1
1
vote
1 answer

How to decode .ogg opus to int16 NumPy array with librosa?

What I'm trying to do I'm trying to transcribe Telegram audio messages, using Mozillas speech-to-text engine deepspeech. Using *.wav in 16bit 16khz works flawless. I want to add *.ogg opus support, since Telegram uses this format for it's audio…
blkpingu
  • 1,556
  • 1
  • 18
  • 41
1
vote
0 answers

Can't install DeepSpeech on Raspberry Pi 4 Virtualbox

Tried to install DeepSpeech via pip3 install deepspeech and got this: Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple Collecting deepspeech Could not find a version that satisfies the requirement deepspeech (from…
Lady_Hangaku
  • 97
  • 1
  • 9
1
vote
1 answer

ValueError: Scorer initialization failed with error code 1

I am new to tensorflow. I am studying the project deepspeechhttps://github.com/mozilla/DeepSpeech, but when I run evauate.py, I get the error: ValueError: Scorer initialization failed with error code 1 the details as follows. Can anybody can help…
kzhangpeng
  • 11
  • 1
1
vote
0 answers

ImportError: DLL load failed: A dynamic link library (DLL) initialization routine failed. (error importing deepspeech python)

I'm trying to run deepspeech's pretrained model using deepspeech's python module on a Windows Server 2016 but getting the following error: Traceback (most recent call last): File "c:\program files\python36\lib\runpy.py", line 193, in…
Shak97
  • 11
  • 1
1
vote
0 answers

Segmentation fault during transcription - DeepSpeech 0.4.1/Spanish

I am using deepspeech 0.4.1, as instructed by the Spanish deepspeech github repo, on a RedHat 7 server with 64GB RAM in order to transcribe Spanish audio. I am getting a “Segmentation Fault" error shorty after it starts processing. Here is an…
Amnon
  • 2,212
  • 1
  • 19
  • 35
1
vote
2 answers

Get alternative suggestions during speech recognition

I would like to use offline speech to text recognition, mostly for German language. Especially, I want to use Mozilla DeepSpeech (a TensorFlow implementation of Baidu's DeepSpeech architecture), but I fear that the audio quality of the audio input…
user7468395
  • 1,299
  • 2
  • 10
  • 23
1
vote
1 answer

Deepspeech training

i tried to run training for small data, using Mozilla DeepSpeech. All requirements are installed. ./bin/run-ldc93s1.sh But i faced this problem: `Loading the LM will be faster if you build a binary file. Reading…
Dmitrii Li
  • 11
  • 2
1
vote
2 answers

Mozilla DeepSpeech on Alpine

I am trying to install DeepSpeech in my Alpine container, and while I seem to fulfill all of the requirements according to the documentation, I get 'not compatible with this Python error'. Here is the log from when I run pip install --verbose…
MadCatm2
  • 951
  • 4
  • 24
  • 41
1
vote
2 answers

Why do the results of this DeepSpeech python program differ from the results I get from the command line interface?

I'm learning about Mozilla's DeepSpeech Speech-To-Text engine. I had no trouble getting the command line interface working, but the Python interface seems to be behaving differently. When I run: deepspeech --model models/output_graph.pb --alphabet…
Display name
  • 721
  • 2
  • 11
  • 29
1
vote
0 answers

Training offline speech-recognition software with half-transcribed interviews

I searched a bit for a speech recognition software that would work offline and allow me to train it with half-finished transcripts. It seems that Mozilla's deepspeech could do the job. The issue of the interviews that I have to transcribe is that…
baloo
  • 517
  • 1
  • 5
  • 13
1 2
3
4 5 6 7