Embedded Offline ASR Engine Development

This project is to use Python and Mozilla’s DeepSpeech ASR (automatic speech recognition) engine on different platforms (such as Raspberry Pi 4, Nvidia Jetson Nano, Windows PC, and Linux PC, Mac) in order to develop a refined ASR engine with source code, instruction, data and an API documentation delivered after development complete.

It is a deep neural network with recurrent layers that gets audio features as input and outputs characters directly — the transcription of the audio, and uses LSTM (Long short-term memory).

This project targets <6% of Word Error Rate, and especially for key phrases and key words to <3% WER, close to human level performance

Compétences : Python, Deep Learning, Machine Learning (ML), Neural Networks, Intelligence Artificielle

en voir plus : expression engine development design india, expression engine development time frame, iphone apps search engine development, expression engine development offshoring team, booking engine development contract, booking engine development plan, outsource developers google app engine development, booking engine development, embedded linux widget engine, fix engine development java, iphone offline map app development, meta search engine development, engine development, offline map application development, music search engine development, social engine development, game engine development, eie: efficient inference engine on compressed deep neural network

Concernant l'employeur :
( 8 commentaires ) Uznoukrainsk, Ukraine

Nº du projet : #25443611

Décerné à:


HI For this project, I'll use latest Mozilla’s DeepSpeech ASR engine which comes with tflite model (TensorFlow Lite),which is faster than real-time on a single core of a Raspberry Pi 4, and will be able to make audio Plus

%selectedBids___i_sum_sub_7% %project_currencyDetails_sign_sub_8% USD en 7 jours
(4 Commentaires)