Code speech to text with Google cloud: Convert WAV to FLAC, by running sox in terminal: sox ZOOM0005_Tr1.wav ZOOM0005_Tr1.flac or use FFMPEG to convert MP3 to FLAC in terminal: ffmpeg -i input.mp3 output.flac Upload file to Google Cloud Storage folder
META (Multilingual Europe Technology Alliance) Prize
The groups winning META Prize are big names, who have contributed to the community useful and practical products for translation and multilingual communications, for example: MOSES: statistical engine for machine translation DGT: alignment of a hugh open database to make
Speech Kitchen’s Virtual Machines
The Speech Recognition Virtual Kitchen, maintained by professors from CMU, OSU and MNSU. Their website: http://speechkitchen.org and repository: https://github.com/srvk Listed below are a few of our speech kitchen virtual machines Prix Fixe — a basic virtual machine for beginners. Excelsior! Interaction in
srvk/eesen-transcriber: EESEN based offline transcriber using models trained on TEDLIUM and Cantab Research
Chương trình này dùng để transcribe (nghe lời nói viết thành chữ) audio và video. Họ giới thiệu là dùng mạng nơ-ron để dạy engine học, dựa trên một số dữ liệu mở. eesen-transcriber This Virtual Machine implements a system