RTF of pre-trained models

The following table lists the RTF of pre-trained models on Raspberry Pi 4 Model B Rev 1.5.

Number of threads	1	2	3	4
vits-melo-tts-zh_en (Chinese + English, 1 speaker)	6.727	3.877	2.914	2.518	163 MB
vits-piper-en_US-glados (English, 1 speaker)	0.812	0.480	0.391	0.349	61 MB
vits-piper-en_US-libritts_r-medium (English, 904 speakers)	0.790	0.493	0.392	0.357	75 MB
ljspeech (English, single-speaker)	6.057	3.517	2.535	2.206	109 MB
VCTK (English, multi-speaker, 109 speakers)	6.079	3.483	2.537	2.226	116 MB
csukuangfj/sherpa-onnx-vits-zh-ll (Chinese, 5 speakers)	4.275	2.494	1.840	1.593	116 MB
csukuangfj/vits-zh-hf-fanchen-C (Chinese, 187 speakers)	4.306	2.451	1.846	1.600	116 MB
csukuangfj/vits-zh-hf-fanchen-wnj (Chinese, 1 male)	4.276	2.505	1.827	1.608	116 MB
csukuangfj/vits-zh-hf-theresa (Chinese, 804 speakers)	6.032	3.448	2.566	2.210	117 MB
csukuangfj/vits-zh-hf-eula (Chinese, 804 speakers)	6.011	3.473	2.537	2.231	117 MB
aishell3 (Chinese, multi-speaker, 174 speakers)	0.365	0.220	0.171	0.156	30 MB
en_US-lessac-medium (English, single-speaker)	0.774	0.482	0.390	0.357	61 MB
matcha-icefall-zh-baker (Chinese, 1 female speaker)	0.892	0.536	0.432	0.391	73 MB