https://github.com/rashadgarayev/trspeech-to-text

https://github.com/rashadgarayev/trspeech-to-text

deepspeech mozilla speech-recognition tensorflow tensorflowdeepspeech turkish-language

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/rashadgarayev/trspeech-to-text
• Owner: RashadGarayev
• Created: 2020-01-24T13:59:44.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-25T01:33:25.000Z (over 1 year ago)
• Last Synced: 2024-10-31T11:42:01.443Z (13 days ago)
• Topics: deepspeech, mozilla, speech-recognition, tensorflow, tensorflowdeepspeech, turkish-language
• Language: Python
• Size: 14.2 MB
• Stars: 17
• Watchers: 4
• Forks: 2
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# A TensorFlow implementation of Baidu's DeepSpeech architecture

 

----------

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.

## Training Your Own Model

https://github.com/mozilla/DeepSpeech/blob/master/doc/TRAINING.rst#training-your-own-model

'Turkish Language  TSV file'

https://voice.mozilla.org/tr/datasets

### Installation

-----------

    

    git clone https://github.com/mozilla/DeepSpeech

    cd DeepSpeech

    pip3 install -r requirements.txt

    pip3 install deepspeech

    

To install and use deepspeech all you have to do is:

   

   pip3 install deepspeech

   

   

   

   

   ### pre-trained Turkish model 

   For the language model, I used kenlm’

   lmplz -o 2 < vocabulary > text.arpa

   build_binary text.arpa lm.binary

   

   ##### after training 

    loss = 6.42

   

    /model/output_graph.pb

     

   

## Training model

    sudo ./run-ldc93s1.sh

    

    Quicker inference can be performed using a supported NVIDIA GPU on Linux. See the `release notes `_ to find which GPUs are supported. To run ``deepspeech`` on a GPU, install the GPU specific package:

   ### Install DeepSpeech CUDA enabled package

   pip3 install deepspeech-gpu

-------------------------------------------------------

## Testing model

#### download lm.binary file from google drive

https://drive.google.com/open?id=1n2VCKosd2JsCVF1TQWIkKbVdeLQf2OYJ

deepspeech --model '/model/output_graph.pb' --lm '/data/lm/lm.binary' --trie '/data/lm/trie' --audio example.wav

-------------------------------------------------------

## Real-time DeepSpeech Analysis 

   python code example

https://discourse.mozilla.org/t/real-time-deepspeech-analysis-using-built-in-microphone/42669