niksedk
commented
1 week ago I don't see anyway to do this with these parameters:
usage: piper [options]
options:
-h --help show this message and exit
-m FILE --model FILE path to onnx model file
-c FILE --config FILE path to model config file (default: model path + .json)
-f FILE --output_file FILE path to output WAV file ('-' for stdout)
-d DIR --output_dir DIR path to output directory (default: cwd)
--output_raw output raw audio to stdout as it becomes available
-s NUM --speaker NUM id of speaker (default: 0)
--noise_scale NUM generator noise (default: 0.667)
--length_scale NUM phoneme length (default: 1.0)
--noise_w NUM phoneme width noise (default: 0.8)
--sentence_silence NUM seconds of silence after each sentence (default: 0.2)
--espeak_data DIR path to espeak-ng data directory
--tashkeel_model FILE path to libtashkeel onnx model (arabic)
--json-input stdin input is lines of JSON instead of plain text
--debug print DEBUG messages to the console
-q --quiet disable loggingYou might be able to compile it with gpu using the Python source, but that's ... too much.
CPU is also pretty fast, so I do not think this is important.
About burn-in, it's a good idea, but you can also do that by using ASSA format.
HI its great software thankyou for all you have done with Subtitle Edit
When converting an .srt to TTS using Piper in Subtitle Edit, the it uses the CPU and there is no GPU option/tickbox.
I think there is a GPU -- accelerator flag when using Piper TTS in teh commandline, Could you please incorporate that use GPU option , thankyou
A second feature request is it would be good to have presets in the 'burn subs to video' layout section, eg a 1) lower 2) middle , 3) upper burn in position would be a great start , also a preset for 'burn in subs ' size/positio for vertical video would be very convenient
thankyou Shorey