FMtoTEXT

The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

This recipe is about transcribing FM radio shows with Speech Recognition.

Download the python script for that:

git clone https://github.com/randaller/fm2txt.git

Follow the installation instructions BUT first erase the pyaudio and speech_recognition from the requirements file. After installing whats in the requirements file (pip install -r requirements.txt) do this:

pip install SpeechRecognition

sudo apt-get install libasound-dev
sudo apt-get install portaudio19-dev
pip install pyaudio –user

Skip the instructions for copying the libraries as it is for Windows and do this (instructions followed: https://osmocom.org/projects/rtl-sdr/wiki/Rtl-sdr):

sudo apt install cmake
sudo apt-get install libusb-1.0-0-dev

git clone git://git.osmocom.org/rtl-sdr.git
cd rtl-sdr/
mkdir build
cd build
cmake ../
make
sudo make install
sudo ldconfig

cmake ../ -DINSTALL_UDEV_RULES=ON

Try

python listen.py --freq=95000000

if you get this error: Kernel driver is active, or device is claimed by second instance of librtlsdr. In the first case, please either detach or blacklist the kernel module (dvb_usb_rtl28xxu), or enable automatic detaching at compile time. usb_claim_interface error -6, then do this:

sudo rmmod dvb_usb_rtl28xxu rtl2832

add:

blacklist dvb_usb_rtl28xxu

blacklist rtl2832

blacklist rtl2830

to:

/etc/modprobe.d/blacklist.conf