haozes
I removed the TinyLog dependence , update to swift 5 . check it out https://github.com/haozes/HFSwipeDemo
have same problem here. after convert my fine-tuned model, it take low time on decode time: ``` whisper_print_timings: load time = 73.56 ms whisper_print_timings: fallbacks = 2 p / 1...
add: -nf, --no-fallback [false ] do not use temperature fallback while decoding now it works ``` whisper_print_timings: load time = 62.46 ms whisper_print_timings: fallbacks = 0 p / 0 h...
来试试
I think i got the problem pocketsphinx needs 16KHZ samples. the iPhone7/iOS10 default record audio format is 44.1K 2 channels sample.here is my code let formatIn = input.inputFormat(forBus: 0) let...
Yes, I test it on real device. I use it to keyword spotting(Chinese Language),the model is download form pocketsphinx package. PS: TLSphinx only output result after speech stop , output...
but we don't want the whole Nav SDK 😂